Inpainting
-
TransGHOST: Real-Time, Synthesis-Free Reconstruction of Instrument-Occluded Regions in Ophthalmic Microsurgery
2026-11-10 12:08:36Niran Nataraj, Maina Sogabe, Masamichi Yamashita, Norihiko Ito, Kenji KawashimaAbstract
Intraoperative scene perception in ophthalmic microsurgery is limited by instrument occlusion: when a tool enters the high-magnification field, it conceals tissue from both the surgeon and the perception components of robot-assisted systems that process the video. Generative inpainting can remove the occluder but replaces the missing image content with synthesis, which is unsuitable when visual provenance matters. Many video inpainters also depend on future frames and cannot operate online. We present TransGHOST, a causal reference-guided reconstruction pipeline whose non-generative safe mode operates in real time. Every restored value is obtained by resampling a recorded frame using geometric transforms fitted only to visible regions. The system provides per-pixel confidence and provenance and marks unsupported pixels as abstentions. We evaluate TransGHOST on a new veterinary clinical corpus of canine cataract surgery with pixel-level instrument and anatomy labels. Only the occluded region is scored, and each scoring target is verified to differ from the reference supplied to the system. Safe mode reaches 31.89 dB masked PSNR and 0.915 masked SSIM at 51.7 ms median and 85.5 ms 95th-percentile latency. On a pre-declared held-out cohort using instrument cutouts excluded from segmentation training, it reaches 29.83 dB masked PSNR, while matched-mask evaluation on validation shows a 3.45 dB advantage over LaMa. Region-aware reference selection improves masked PSNR by 3.60 dB over recency when candidate references can themselves be occluded. Reference-age analysis further defines the operating interval for the brief, repeated occlusions targeted by TransGHOST.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13971
PDF
-
MusicFlux: Flexible Conditioning for Text-Guided Music Generation and Editing
2026-11-10 10:00:03Teysir Baoueb (IP Paris, LTCI, IDS, S2A), Leonardo Boulitreau de Menezes Martins Marques (IP Paris, LTCI, IDS, S2A), Paraskevas Stamatiadis (S2A, LTCI, IDS), Ga{\"e}l Richard (S2A, IDS, IP Paris, LTCI)Abstract
Music editing transforms existing recordings while preserving their original attributes. Recent approaches adapt pretrained text-to-music models for tasks like inpainting, event insertion, or restoration by conditioning them with context audio. It was recently proposed for image editing to unify generation and editing by treating the source image as in-context information. However, applying this directly to music is computationally expensive due to long audio sequences. In this work, we develop MusicFlux, a text-guided music editor built on an efficient pretrained flow-matching text-to-audio model. We introduce two conditioning approaches that trade off editing performance and computational efficiency. Experiments show that both are competitive with strong baselines, with one achieving better editing quality and the other preserving the original sequence length and substantially improving computational efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13834
PDF
-
WAM is capable in BEHAVIOR-1K: the 2nd-place solution to the 2026 BEHAVIOR Challenge
2026-11-10 09:46:02Yelin He, Jiaquan Ye, Xinming Wei, Wenjie Xiao, Gengming Zhang, Guoting Wei, Xianbiao Qi, Rong XiaoAbstract
This work presents the 2nd-place solution (Team IF1001) to the 2026 BEHAVIOR Challenge, which evaluates mobile manipulation across 100 household tasks. Our method is built on a powerful world action model (WAM), Cosmos 3. We improve Cosmos 3 by using richer visual history, task-progress conditioning, and task-group and skill-specific LoRA adapters. During inference, we apply a separate progress estimator to supply task-progress context, and use task- and progress-conditioned routing to select a task-group or skill-specific policy, complemented by action-candidate aggregation, rolling inpainting, and task-specific temporal and gripper control. To meet the minimum inference requirement of 1 FPS, we use neither recursive self-improvement (RSI) nor agentic harness methods and rely on no closed-source models; during official private-test evaluation, our system handled concurrent requests across 100 evaluation ports with limited hardware resources, sustaining an average end-to-end inference rate above 2 FPS per port. Our method achieves a mean Q-score of 0.613 and a full-task success rate of 40.9%, averaged over 3 self-evaluation rounds across all 100 tasks. On the official private test set, with 20 instances per task, our system achieves a mean Q-score of 0.615 and a full-task success rate of 41.2%.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13818
PDF
-
Comparative Evaluation of Deep Learning Models for Geographic Atrophy Segmentation in En Face OCT Images
2026-11-09 20:12:13Utkarsh Doshi, Adarsh Gadari, Sharat Chandra Vupparaboina, Joseph DeCicco, Giulia Gregori, Nicola Valsecchi, Nasiq Hasan, Elham Sadeghi, Jos\`e-Alain Sahel, Jay Chhablani, Kiran Kumar Vupparaboina, Sandeep Chandra BollepalliAbstract
Background: Geographic atrophy (GA) is an advanced form of age-related macular degeneration (AMD). It causes irreversible vision loss due to progressive degeneration of the retinal pigment epithelium (RPE) and photoreceptors. Accurate segmentation of GA in en-face image is crucial for early diagnosis, monitoring disease progression, and developing personalized treatment strategies. However, existing deep learning approaches are typically evaluated using single architectures and single-device datasets, limiting insight into relative performance and cross-device robustness. Methods: We trained and systematically compared five deep learning architectures for GA segmentation: Nested U-Net, ResU-Net, nnUnet, Swin-Unet and MedSegDiff model, together with a thresholding based classical baseline. The models were trained on a dataset of en-face OCT images derived from 269 OCT volumes from two different devices, following a three-step preprocessing technique involving normalization and inpainting to enhance the quality of the en-face images. Results: On the fixed held-out validation set comprising OCT scans from both Cirrus (R) (Carl Zeiss Meditec, Inc., USA) and Spectralis (R) (Heidelberg Engineering, Germany) devices, nnUnet achieved the highest mean Dice similarity coefficient (DSC) of 0.8882 +/- 0.0033. The other models yielded the following Dice scores: Nested U-Net (0.7932 +/- 0.0423), ResU-Net (0.8453 +/- 0.0074), Swin-Unet (0.6886 +/- 0.0294), and Diffusion model (0.7959 +/- 0.0242). Conclusions: nnUnet framework, demonstrated most reliable performance for GA segmentation in en-face OCT under limited data conditions. It offers the best balance of accuracy, stability, and efficiency for GA quantification.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13191
PDF
-
Seeing Is Not Believing: Counterfactual Lesion Erasure Teaches a Small Medical Vision-Language Agent to Report Only What the Image Shows
2026-11-08 23:09:18Bhaskar GurramAbstract
Medical vision-language models (VLMs) often report a finding because the question names it; standard benchmarks miss this. From public segmentation datasets we build counterfactual views without manual annotation: the lesion erased by inpainting, a same-shape control edit elsewhere, and unedited lesion-free images. The evidence sensitivity gap (ESG) is the rate of absent-or-refer answers after erasure minus the rate after the control edit; it is zero for a model that ignores the image or reacts to both edits alike. MedScope-4B (Qwen3.5-4B, LoRA, image tools) was trained on label-derived trajectories, selected by a pre-registered rule and tested once against nine frontier and six open VLMs; four pre-registered checks then probed the mechanism. On 507 internal cases across five imaging types, MedScope-4B reached ESG 0.758 and claimed an erased lesion in 9.6% of cases, against 0.27-0.47 and 41-62% for the frontier models (all p<0.001), without significant loss of accuracy on real lesions. Without counterfactual views ESG fell to 0.279+-0.107 (three seeds); the effect replicated on MedGemma 1.5 4B and two unseen inpainting tools. At four external centres the advantage held but frontier models detected more real lesions; on a fresh external test MedScope-4B detected 0 of 48 pneumothorax films, with net utility below gemini-4-argon's (-0.36 [-0.50, -0.23]). Matching the control edit was not shown to matter; over three seeds no fresh-external ESG advantage over removal-based DPO was established; a paired-view consistency objective did not beat a matched-compute control, while that continuation alone cut erased-lesion claims on unseen tools at every seed, at a cost in sensitivity at one. Training on erased and edited images gives a small model an evidence-gated disposition that prompting does not give frontier models; it does not improve perception, and rare critical findings need coverage.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13006
PDF
-
JEPAhead: From Inpainting to Causal Forecasting for Urban Driving
2026-11-05 20:06:13Daniel G. P. Petrini, Davi Pincinato, Fabio Grassiotto, Pedro L. F. Prado, Alexandre F. S. Osorio, Raphael V. Ramos, Felipe PamboukianAbstract
We fine-tune a pre-trained V-JEPA1 predictor from bidirectional latent inpainting to action-free causal forecasting while keeping the encoder frozen. Using contiguous past observations, horizon-aligned targets, and group-level causal attention, the model forecasts eight future token groups, corresponding to sixteen frames, in one forward pass. On CARLA Town12, it retrieves the correct future among 591 candidates in 69.0% of cases, compared with 55.3% for persistence, with greater gains at longer horizons and on tokens exhibiting greater change. It also outperforms a compact predictor trained from scratch with six times fewer parameters. Semantic analysis indicates driving-relevant information in predicted features: a fixed linear probe trained on real encoder tokens achieves 0.16 mIoU on patches undergoing semantic-class changes, versus 0.13 for persistence. Vehicle-conditioned retrieval improves over persistence by 15 percentage points at the longest horizon. Pixel-space evaluation shows modest L1 gains but little improvement under LPIPS, motivating direct evaluation through latent and semantic measures alongside an oracle reconstruction reference. These findings support further investigation of latent forecasting for driving perception, while downstream utility remains unverified.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08657
PDF
-
Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification
2026-11-04 10:17:04Dung Do Tien, Kien Nguyen Do Trung, Kiet Dang Vu, Trung Thai Tran, Duc Dung NguyenAbstract
While recent feed-forward 3D Gaussian Splatting methods enable efficient driving-scene reconstruction from surround-view images, their reliance on a single observation fundamentally hinders novel-view synthesis. Regions occluded in the input can become visible from novel viewpoints, leaving the reconstructed Gaussians under-constrained and incomplete. Moving beyond image-space inpainting for rendered views, we introduce OccSplat, a feed-forward framework whose core contribution is Occlusion-Aware Gaussian Densification, explicitly targeting missing scene geometry rather than missing pixels. By predicting new Gaussian primitives for unsupported regions, OccSplat completes the scene directly in the 3D representation. Specifically, OccSplat first identifies occluded regions that lack Gaussian support through Gaussian Occlusion Mapping. Gaussian Occlusion Completion then generates new primitives for these regions. The predicted primitives are integrated into the original representation to improve novel-view synthesis while retaining feed-forward inference without per-scene optimization. Experiments on the nuScenes benchmark demonstrate that OccSplat improves on the compared methods and yields particularly large gains in occluded regions, leading to more accurate and visually coherent driving-scene reconstruction.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06273
PDF
-
Rethinking Data Imbalance in Class Incremental Surgical Instrument Segmentation
2026-10-26 06:52:40Shifang Zhao, Long Bai, Kun Yuan, Feng Li, Jieming Yu, Wenzhen Dong, Guankun Wang, Mobarakol Islam, Nicolas Padoy, Nassir Navab, Hongliang RenAbstract
In surgical instrument segmentation, the increasing variety of instruments over time poses a significant challenge for existing neural networks, as they are unable to effectively learn such incremental tasks and suffer from catastrophic forgetting. When learning new data, the model experiences a sharp performance drop on previously learned data. Although several continual learning methods have been proposed for incremental understanding tasks in surgical scenarios, the issue of data imbalance often leads to a strong bias in the segmentation head, resulting in poor performance. Data imbalance can occur in two forms: (i) class imbalance between new and old data, and (ii) class imbalance within the same time point of data. Such imbalances often cause the dominant classes to take over the training process of continual semantic segmentation (CSS). To address this issue, we propose SurgCSS, a novel plug-and-play CSS framework for surgical instrument segmentation under data imbalance. Specifically, we generate realistic surgical backgrounds through inpainting and blend instrument foregrounds with the generated backgrounds in a class-aware manner to balance the data distribution in various scenarios. We further propose the Class Desensitization Loss by employing contrastive learning to correct edge biases caused by data imbalance. Moreover, we dynamically fuse the weight parameters of the old and new models to achieve a better trade-off between the biased and unbiased model weights. To investigate the data imbalance problem in surgical scenarios, we construct a new benchmark for surgical instrument CSS by integrating datasets. Extensive experiments demonstrate the effectiveness of the proposed framework, achieving significant performance improvement against existing baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34925
PDF
-
Finetuning Prompt-Based Image Editor for Geometry-Consistent Room Defurnishing
2026-10-25 21:54:21Prakhar Kulshreshtha, Brian Pugh, Zachary Nussdorfer, Salma JiddiAbstract
Erasing all furniture from a single room image to generate its empty counterpart is valuable for XR applications such as diminished reality and virtual staging. The challenge is twofold: inpainting the furniture regions with realistic content, and doing so without distorting the room's 3D geometry. Prompt-driven image editors, such as FLUX.2, handle realism impressively, but their structural faithfulness is inferior to explicit layout conditioned inpainting. To improve geometric consistency, we propose a training recipe for finetuning a LoRA on 2,500 furnished-empty room pairs. FLUX.2 with our LoRA adaptor significantly improves geometric consistency while retaining the high texture fidelity. This single-photo inpainter can be an effective building block for depth-aware and 3D-consistent XR pipelines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34597
PDF
-
Support-guided OOD Removal with Diffusion
2026-10-23 18:41:53Alireza Kheirandish, Sara Fridovich-KeilAbstract
Many real-world signals are corrupted by localized, structured perturbations whose distribution is unknown: an intermittent background noise in a music recording, a watermark stamped on a photograph, a cast shadow. We study the task of recovering a clean signal $x$ from an observation $y$ containing such a localized out-of-distribution (OOD) corruption. We propose Support-guided OOD Removal with Diffusion, SORD, an iterative algorithm to recover $x$ using only two ingredients: a binary map of the corruption support and a single diffusion model pretrained on clean signals. SORD does not require any paired data or any statistical model of the corruption. We evaluate SORD on natural images and human faces with spatially localized corruptions including handwritten digits, other images, watermarks, and shadows, as well as audio recordings of different musical instruments with temporally localized corruptions including other instruments and human speech. SORD is competitive with, and often outperforms, posterior-sampling inpainting given the same diffusion prior and the same mask, source-separation baselines that require a separate diffusion model for each source, and, on several benchmarks, supervised networks trained on paired clean and corrupted signals. The code is released here: \href{this https URL}{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33194
PDF
-
TravSUITE: Traversability via Self-Supervised, Uncertainty-Aware IRL and Terrain Estimation
2026-10-23 03:56:47Samuel Triest, Amirreza Shaban, David D. Fan, Wenshan Wang, Sebastian SchererAbstract
Traversability analysis in off-road settings remains a fundamental challenge for mobile robots. Key difficulties include constructing an accurate and expressive local map from multimodal sensor data, and using the map to design traversability rules that yield desirable navigation behavior. Importantly, this system must be resilient to the limited sensing regime brought about by complex environments and high speeds. In this paper, we present TravSUITE, a traversability system suitable for high-speed navigation in off-road environments. TravSUITE consists of two major components: 1) an efficient voxel mapper that leverages visual foundation models (VFMs) to build a rich geometric-semantic local map from streams of on-board sensor data, and 2) a unified neural network that jointly predicts traversability-relevant quantities in bird's eye view (BEV), including geometry, semantics, speed and cost. Our training strategy is entirely annotation-free and self-supervised, leveraging tasks such as map inpainting and inverse reinforcement learning (IRL) to learn both map representations and traversability. We perform a thorough ablation study and comparison to state-of-the-art approaches, and the results indicate that cost learning and auxiliary inpainting each contribute significantly to planning quality, and their combination is critical for achieving state-of-the-art performance in off-road path planning. We also design a simple risk adaptation mechanism to leverage our method's uncertainty estimates at deploy-time, and demonstrate that a combination of inpainting and risk estimation can result in 80% fewer navigation errors and 5% faster autonomous traversal speeds in real-world hardware experiments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32130
PDF
-
Scaling Transformer Energy-based Models For High Quality Image Synthesis
2026-10-22 20:39:10Jungsoo Lee, Alexi Gladstone, Yilun DuAbstract
Energy-Based Models (EBMs) are a flexible class of generative models that decouple probabilistic modeling from the generation process. This decoupling directly enables compositional generation and inference-time scaling, where sample quality can be refined simply by increasing sampling steps. However, severe challenges in high-dimensional sampling and training instabilities with deep architectures have restricted EBMs to low-dimensional regimes. To resolve these bottlenecks, we introduce the Transformer Energy-Based Model (TEM), a scalable transformer energy function operating entirely within a latent space. On top of this backbone, we extract energies at multiple layers and sum them, composing complementary constraints from local texture to global semantics. Furthermore, two components make this high-quality at scale: Positive Representation Alignment (PRA), which supervises TEM's intermediate representations with a vision foundation model, and advanced sampling strategies that improve sample quality at inference. TEM-XL achieves an FID-50K of 3.82 on class-conditional ImageNet 256$\times$256 without classifier-free guidance, showing that a contrastive EBM can generate high-fidelity images. On ImageNet 512$\times$512, TEM achieves an FID-50K of 8.24, demonstrating that the approach scales to higher resolution. We further validate the core promises of EBMs: compositional generation, zero-shot inpainting, and out-of-distribution detection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31889
PDF
-
UniVOE: A Removal-Driven Framework for Interaction-Aware Universal Video Object Editing
2026-10-22 17:54:03Shuzhou Yang, Lanqing Guo, Lingen Li, Weiqi Li, Zhao Zhong, Liefeng Bo, Jian ZhangAbstract
Video object removal and injection are reciprocal editing operations between object-present and object-absent video states, yet they differ substantially in training difficulty. Removal can be effectively bootstrapped from video inpainting and further adapted to erase object-related interaction effects. Injection, however, requires large-scale paired supervision to model object appearance, dynamics, and scene-dependent effects, while perfectly aligned real-world pairs are difficult to collect and synthetic data lacks sufficient realism and diversity. To address this challenge, we present UniVOE, a removal-driven framework for training both video object removal and injection models. We first train an effect-aware remover by transferring video inpainting priors and finetuning on object-present/object-absent pairs. The trained remover converts real object-present videos into object-absent counterparts, creating large-scale paired supervision for injection. An injection model is trained on these pairs in the reverse direction to recover objects together with their dynamics and interaction effects. Moreover, since pixel-level reconstruction alone cannot adequately capture perceptual realism, we introduce a reward-based post-training method that aligns injection results with human preferences using a proprietary reward model. Experiments against strong open-source and commercial systems demonstrate that UniVOE achieves state-of-the-art performance on both object removal and injection, particularly in challenging interaction-effect cases.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31641
PDF
-
Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion
2026-10-22 10:06:42Ricardo Luna Gutierrez, Vineet Gundecha, Rahman Ejaz, Varchas Gopalaswamy, Riccardo Betti, Sahand Ghorbanpour, Aarne Lees, Soumyendu SarkarAbstract
The achievement of practical fusion energy remains one of the most pressing unsolved scientific challenges, with immense implications for carbon-free power. A critical factor in the success of Inertial Confinement Fusion (ICF) is the design of a Laser Pulse Shape (LP) that can optimally drive implosions under stringent physical constraints. Traditional LP design relies on computationally expensive simulations and manual iterative refinement. We introduce the ICF Laser Pulse Shape Design System (LPDS), a generative inverse modeling framework that maps desired outcomes and target pellet configurations directly to optimized LPs. Crucially, we design a multi-objective loss function to ensure the generated LPs satisfy fundamental physical constraints and experimental requirements. Furthermore, we present constraint-conditioning, inpainting, and gradient-based LP editing mechanisms for fine-grained control over specific pulse characteristics during generation. Moreover, we study the transfer of our framework to a limited set of real experimental shots. Our method establishes a data-driven inverse design framework for LP design in ICF, contributing to the advancement of practical and sustainable fusion energy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33096
PDF
-
ROCOCO: Robust Outline Completion of Occluded Curvilinear Objects
2026-10-21 04:09:17Ken Zheng, Jaimyn DrakeAbstract
We propose a learning-based generative model for completing curvilinear features under occlusion by environmental obstacles. To this end, we adopt a flow matching-based approach that supports the inpainting of occluded regions with the appropriate curvilinear features. To eliminate the reliance on privileged information about the occlusion a priori, we also train a UNet-based mask prediction model, which can identify regions for inpainting given only the occluded observation. The components of our approach are validated via experiments using procedurally-generated test cases, and the complete pipeline is validated using large public datasets for curvilinear objects. Against off-the-shelf inpainting baselines, ROCOCO is the strongest method by a wide margin when no occlusion mask is given, and is competitive with mask-supervised inpainting when one is, achieving best on full-image error and second only to LaMa on the occluded region, while using a completer of $7.7$M parameters against LaMa's $51$M and Stable Diffusion's $860$M.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29177
PDF
-
Edit in Sync: Unified End-to-End Audio-Visual Editing for Human-Centric Videos
2026-10-20 09:53:32Ziye Yuan, Minghong Cai, Xu He, Ruchang Yao, Xiao Fu, Kaixin Ding, Ming Zhang, Xiangyu Du, Tianpeng Lan, Da Xie, Xiangyu YueAbstract
Human-centric audio-visual editing requires precise alignment of lip movements, gestures, and expressions with speech. Existing methods process inputs through independent video and audio pipelines, preventing cross-modal interaction between visual editing and audio dubbing. Many of these pipelines further rely on mask-based inpainting. As a result, they suffer from poor lip-audio synchronization, cumulative pipeline errors, and an inherent mask-size dilemma. We present AVE, the first unified end-to-end framework that jointly performs reference-guided person swapping, insertion, and deletion across both audio and video modalities without requiring spatial masks. To overcome data scarcity, we design a synthesis pipeline and introduce AVE-Dataset, the first audio-visual editing dataset to provide 100K pairs with appearance and voice references. By combining Synthetic-to-Real reconstruction with preliminary audio warm-up, our framework transcends synthetic pipeline limits and mitigates audio-video token imbalance. AVE outperforms modality-separate audio-visual editing pipelines in editing realism, temporal consistency, and audio-visual alignment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27947
PDF
-
Learning to Correct Geometry in Generated Videos
2026-10-16 17:59:55Weijie Lyu, Tiancheng Shen, Jason Li, Yujing Wang, Xiaoyuan Wang, Haobo Yuan, Yizhou Zhao, Ming-Hsuan YangAbstract
Generated videos often lose geometric consistency under camera motion: structures warp under viewpoint change, parallax becomes inconsistent, and smooth camera movement may collapse into shot-like transitions. We argue that this failure is largely a data problem. In web-scale video corpora, most visible motion comes from dynamic objects captured by static or weakly moving cameras, leaving only sparse supervision for viewpoint-induced appearance changes. To address this, we propose Video Geometry Corrector (VGC), a post-hoc video-to-video model trained on synthetic paired supervision. Starting from real videos with diverse camera motion and pose annotations, we construct VG-Pairs with a synthetic paired-supervision data generation pipeline. Each video clip is treated as a geometry-consistent target and paired with a distorted counterpart synthesized by a pretrained image-to-video inpainting model using trajectory-adaptive keyframes. VGC learns to map the distorted input to the geometry-consistent target without modifying the source generator, and uses optical flow as an auxiliary cue to help disentangle camera motion from object motion. Experiments on pose-conditioned and prompt-driven benchmarks show that VGC improves geometric consistency across multiple source generators, and scaling to a larger backbone further extends the framework toward more general video refinement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23856
PDF
-
Robotic Spatiotemporal Editing: A Unified Interface for Controllable Action Generation via Masked Action Reconstruction
2026-10-16 06:25:32Yanbang Li, Bu He, Yi Tian, Yu-Chiao Huang, Chenyu Zhang, Ruoqu Chen, Yuanzhe Liu, Yuxiang Gao, Mengdi XuAbstract
Generative policies can synthesize robot behaviors, yet controlling and editing them through diverse spatiotemporal references remains challenging. In the real world, human intent requires robot behaviors that satisfy constraints on where, when, and how actions are executed. Our key insight is that spatiotemporal control references, such as keypoints, flows, orientations, and keyposes, can be viewed as partial specifications of the same temporal Cartesian action space. We introduce the MAP (Masked Action Space) interface to unify these action references and formulate controllable manipulation as an action inpainting problem. Our Inpainting Policy (IP) reconstructs missing action dimensions of the end-effector, combining progress-guided alignment with multi-mask training to support unseen action-constraint combinations. We further adopt a training-free RePaint variant that iteratively inpaints the action during denoising to reduce control error. On ManiSkill and LIBERO-10, our policy achieves average task success rates of 92.67% and 64.67%, this http URL-world experiments demonstrate spatiotemporal control with average positional and rotational errors of 44.3 mm and 7°, respectively, showing that our policy can use diverse references to guide executable robot behaviors.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23002
PDF
-
DINO-FIL: Multi-Layer Transformer Fusion for Generative Inpainting Forgery Localization
2026-10-15 12:36:53Simon Freitter, David Fischinger, Silvia Poletti, Marcel Hasenbalg, Martin BoyerAbstract
We propose DINO-FIL, a transformer-based framework for pixel-level localization of generative image forgeries. The method leverages multi-layer representations from a pretrained DINOv3 ViT-H+/16 encoder combined with a lightweight fusion decoder to capture both semantic structure and fine-grained texture inconsistencies introduced by image editing. By aggregating intermediate transformer features across depths, the model improves sensitivity to subtle, spatially localized artifacts that are often missed by standard single-layer approaches. We evaluate DINO-FIL in a cross-dataset setting, training on B-Free and testing on Beyond the Brush, CocoGlide, TGIF, and SAGI-D. The model achieves strong generalization, outperforming existing baselines on average and on four of five evaluated datasets, while maintaining a high true negative rate on pristine images.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21780
PDF
-
Spurious Attention Heads in Vision Transformers: Mechanistic Identification of Annotation-Driven Bias in Medical Chest X-Ray Analysis
2026-10-15 10:21:14Joshua Muhumuza, Cornelius KalenziAbstract
Vision Transformers deployed in medical imaging exploit spurious correlations, yet the internal mechanisms remain unidentified and impossible to fix. We apply mechanistic interpretability to locate one such mechanism in ViT-Base 16: a single attention head (L8H10) that functions as a dedicated annotation-reader on chest X-rays, attending to corner text rather than lung pathology in 62% of 200 COVID-19 images. Causal validation via inpainting confirms annotation content rather than luminance or edge density drives the behaviour, increasing lung attention 1.52 times upon removal in affected images ($p{<}0.0001$). The finding replicates across NIH ChestX-ray14 (79%), DeiT-Base (88%), and ViT-Large 16 (80%), establishing spurious annotation-attending heads as a consistent property of ViT-family architectures across two datasets and three architectures. Full fine-tuning does not suppress the behaviour and may entrench it: 98.4% of spurious images remain spurious and the spurious rate rises marginally, as the shortcut is reinforced rather than removed. Critically, single-head ablation produces $p{=}0.340$ and multi-head ablation of all three identified carriers produces $p{=}0.532$, meaning a causally verified annotation-reading circuit is completely invisible to output-level evaluation. Mechanistic auditing finds what behavioural testing cannot.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21638
PDF
