arXiv:2608. 06075v1 Announce Type: cross Abstract: Commercial vision-language models are reshaping computer vision, with visual priors broad enough to rival task-specific systems.
Commercial vision-language models are reshaping computer vision, with visual priors broad enough to rival task-specific systems. This raises a natural question: do they reduce the need for classic, physics-informed low-level vision?
The paper introduces AgenticShadow, a new dataset of 17,138 image‑mask‑target triplets created through an offline agentic workflow that combines physics‑motivated generation, failure detection, feedback‑driven retry, candidate selection, and deterministic correction. This approach addresses the long‑standing lack of diverse paired shadow‑free training data by leveraging existing shadow detection datasets and producing realistic shadow‑free targets. Models trained on AgenticShadow show significant improvements, reducing color distribution differences by 50.5% and cross‑domain LAB RMSE by 19.7‑37.5% compared to prior work.
The paper introduces a counterfactual benchmark to evaluate whether vision models understand physical constraints or merely learn rendering shortcuts. Using Mitsuba 3, it generates 5,500 synthetic images across 500 scene families, each with a clean image and ten violations (shadows, reflections, support, surface response, occlusion). Diagnostic baselines (LLaVA‑1.5‑7B, Qwen2.5‑VL‑7B, InternVL3.5‑8B) achieve 64.0–67.8 % macro‑F1 on a held‑out synthetic test set, but performance drops to 40.8 % for LLaVA‑1.5‑7B under an intervention shift, indicating reliance on rendering cues rather than true physical reasoning.
Material replacement is a common interior-design operation: changing the material of a selected surface while preserving its geometry, surroundings, and illumination. Despite its commercial relevance,...
MatReplace is a new reference‑free benchmark for evaluating material replacement in interior scenes, assessing edits on local material correctness, global lighting harmony, outside preservation, and inside structure. It offers three tracks that vary the conditioning signal—instruction only, instruction plus region mask, and material reference image—allowing systematic comparison of different editing approaches. Results show that while closed‑source editors excel at named‑material rendering, grounding materials from pixel references remains a significant challenge.
arXiv:2512.06174v3 Announce Type: replace Abstract: Generating realistic cast shadows for inserted foreground objects requires reasoning about scene geometry and illumination. However, most learning-...
arXiv:2608.23238v1 Announce Type: new Abstract: We present Mover360, a controllable object manipulation framework for 360{\deg} images. Unlike perspective images, 360{\deg} images in equirectangular...
OccludeBench is a manually curated benchmark that tests vision‑language models (VLMs) on their ability to recover fully occluded objects from remaining visual evidence. The benchmark distinguishes direct cases—requiring recovery from a specific physical cue such as a shadow or reflection—from inferential cases, which rely on broader scene context. Across five VLMs, accuracy averages 42.7 % on direct cases versus 62.7 % on inferential cases, a 20‑point gap, while humans achieve 63.4 % and 68.5 % respectively with no significant gap. The study introduces OccludeTrace, a four‑stage diagnostic that isolates the failure point, revealing that models struggle most when recovering the relevant object from the full image projection. Interventions such as inpaint‑then‑confront reduce the gap to a statistically non‑significant difference for models with image‑generation capabilities.
arXiv:2604.19254v2 Announce Type: replace Abstract: Popular low-rank parameter-efficient fine-tuning (PEFT) methods represent adaptation as separate updates to selected backbone weights, without main...
EditHero is presented as the first benchmark for long-horizon, part-level 3D editing, featuring natural-language instructions and target images for both geometry and texture. The benchmark uses a deterministic assembly engine that produces the exact target after each edit, and every sequence is manually reviewed. It compares non-agentic top‑down methods with LLM/VLM agent bottom‑up approaches, finding that the latter follow instructions more closely and preserve unedited parts better, though each edit takes minutes.
WildShadowRemover is a framework that adapts a pretrained video diffusion model for robust in-the-wild video shadow removal using LoRA fine-tuning. It augments the frozen VAE decoder with a detail injection module and introduces a shadow‑mask‑guided frequency‑decomposed modulation module to restore high‑frequency textures while suppressing shadow artifacts, with monocular depth priors providing geometry‑aware guidance. The authors also create WildShadow, a large‑scale paired video shadow removal dataset, and show that their method outperforms existing approaches in shadow removal quality, temporal consistency, and generalization across challenging real‑world scenarios.
Semantically Aligned Gradient-Driven Context-Preserving Image Editing (IABEdit) is a model‑agnostic framework that embeds differentiable semantic verification into the training of generative image editors. By using a frozen vision‑language model to extract spatially‑aware descriptors from ground‑truth edits and a trainable aligner to reproduce them from generated outputs, the residual becomes a gradient that teaches the generator both what to edit and where, without adding inference‑time VLM cost. IABEdit is compatible with various backbones (e.g., U‑Net in Stable Diffusion and MMDiT in FLUX) and improves structural fidelity on MagicBrush, achieves state‑of‑the‑art instruction adherence on RealEdit and EMU Edit, and outperforms the proprietary Gemini agent on the D‑LORD surveillance benchmark under heavy occlusion. "whyItMatters":"IABEdit demonstrates that incorporating semantic verification during training can produce more accurate, well‑localized edits and outperform existing methods even in challenging surveillance scenarios, as shown by its superior metrics and human/GPT‑4o evaluations."