REVIEW 5 cited by
Generative Physical AI in Vision: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by enabling machines to create and interpret visual data with unprecedented sophistication. This transformation builds upon a foundation of generative models to produce realistic images, videos, and 3D/4D content. Conventional generative models primarily focus on visual fidelity while often neglecting the physical plausibility of the generated content. This gap limits their effectiveness in applications that require adherence to real-world physical laws, such as robotics, autonomous systems, and scientific simulations. As generative models evolve to increasingly integrate physical realism and dynamic simulation, their potential to function as "world simulators" expands. Therefore, the field of physics-aware generation in computer vision is rapidly growing, calling for a comprehensive survey to provide a structured analysis of current efforts. To serve this purpose, the survey presents a systematic review, categorizing methods based on how they incorporate physical knowledge, either through explicit simulation or implicit learning. It also analyzes key paradigms, discusses evaluation protocols, and identifies future research directions. By offering a comprehensive overview, this survey aims to help future developments in physically grounded generation for computer vision. The reviewed papers are summarized at https://tinyurl.com/Physics-Aware-Generation.
Forward citations
Cited by 5 Pith papers
-
PhysMirror: Physics-Aware Mirror Object Generation
An end-to-end pipeline lifts text objects to 3D meshes, constructs exact planar-mirror scenes, extracts depth/segmentation priors, and conditions diffusion models to generate physically consistent reflections, measure...
-
Vision Language Models Cannot Reason About Physical Transformation
Current VLMs cannot maintain transformation-invariant representations of number, length, volume or size and instead rely on textual invariance priors that reverse on matched non-conserving controls.
-
VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
A 1,680-question video benchmark shows leading multimodal models lag humans by ~15 points on visual knowledge, and a See-Think-Answer RL-trained model narrows the gap.
-
Canvas3D: Empowering Precise Spatial Control for Image Generation with Constraints from a 3D Virtual Canvas
Canvas3D lets users arrange objects in a 3D canvas generated from a text prompt, then feeds depth, skeleton, and lighting constraints to diffusion models to produce images that match the layout.
-
LLM-to-Phy3D: Physically Conform Online 3D Object Generation with LLMs
An iterative prompt-refinement wrapper around LLM-to-3D generation, using CFD drag, vision-language domain scores, and visual novelty, reports 4.5% to 106.7% DPAR gains over non-refined baselines in car design.
Discussion (0). Sign in to comment.