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?
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.
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.
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.
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-...
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: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...
arXiv:2610.07887v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) integrate understanding and generation, yet their generative behavior is rarely governed by what they understand abo...
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...
We present Fluid-Gen-Zero, a training-free framework for physics-aware fluid-object interaction video generation that decouples physical reasoning from appearance synthesis. Our key insight is to dele...
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.