Skip to main content
GameDev.net gamedev.net

Computer Vision News

The latest Computer Vision coverage curated for game developers.

Printing the Underdetermined: Materializing Multi-solutionness in Figurative Paintings

arXiv cs.GR details a pipeline that turns figurative paintings into multiple plausible 3D interpretations instead of forcing one reconstruction. It samples camera-orbit videos, rebuilds them with 3D Gaussian Splatting, then …

Research arXiv cs.GR · 16 hours, 58 minutes ago
SplashSplat: Reconstructing Splashing Liquids from Real-World Multi-View Videos

arXiv cs.GR details SplashSplat, a new method for reconstructing splashing liquids from real multi-view video. The team pairs a 20-scene benchmark with seven synchronized 4K cameras at 60 fps and …

Research arXiv cs.GR · 16 hours, 58 minutes ago
Human-aware Design Generation: Adding 3D Humans into Graphic Designs

arXiv cs.GR details a model that inserts 3D humans into partial graphic designs, aiming to make layouts feel more deliberate and visually coherent. The system predicts pose, framing, and placement …

Research arXiv cs.GR · 1 day, 16 hours ago
CADSplat: Sparse-View 3D Gaussian Splatting Aided by CAD Models for Robust, Photorealistic Digital-Twin Reconstruction

arXiv cs.GR details CADSplat, a sparse-view 3D Gaussian splatting pipeline that uses CAD models to reconstruct photorealistic digital twins from fewer than 15 posed images. For teams building AR, inspection, …

Research arXiv cs.GR · 1 day, 16 hours ago
Cascaded Non-Line-of-Sight Imaging

Researchers have pushed non-line-of-sight imaging beyond the usual three-bounce assumption, using higher-order light paths to reconstruct hidden objects around one or even two corners. The technique combines ultrafast laser scanning …

Research arXiv cs.GR · 2 days, 16 hours ago
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

PhysStream pushes video generation toward physically meaningful control, letting creators steer motion mid-generation instead of locking in a full schedule up front. The model uses structured scene memory and sparse …

Research arXiv cs.GR · 2 days, 16 hours ago
Frame-Synchronous Hand Gesture Detection by Projected Winding Order

A new hand-gesture method targets frame-accurate synchronization instead of loose classification, using a single projected winding-order signal to detect an open-hand flip. It needs no training data, calibration, or classifier, …

Research arXiv cs.GR · 3 days, 16 hours ago
SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction

SyntheticDoc brings 1,000,000 procedurally generated, high-resolution training images to document unwarping and illumination correction. The dataset pairs each sample with pixel-perfect UV, normal, albedo, and shading maps, aiming to replace …

Research arXiv cs.GR · 3 days, 16 hours ago
Hi-SPAD: Video-Rate Hyperspectral Imaging and Inference with Single-Photon Cameras

Researchers have introduced Hi-SPAD, a video-rate hyperspectral imaging and inference system built around single-photon cameras. The work targets fast spectral capture that could improve material classification, lighting analysis, and other …

Research ACM Graphics · 4 days, 10 hours ago
Recurrent Dynamic Range Extension

A new HDR reconstruction method extends highlights one exposure step at a time instead of solving the full scene in one pass. The recurrent approach is trained on widely available …

Research arXiv cs.GR · 4 days, 16 hours ago
RealSimLoop: Online Real-to-Sim Adaptation via Differentiable Reduced-Order Simulation with Vision Feedback

RealSimLoop uses vision feedback and differentiable reduced-order simulation to adapt deformable-object models online, aiming for quasi-real-time real-to-sim calibration. For teams working on soft-body physics, robotics-style perception, or VFX-heavy interactions, the …

Research arXiv cs.GR · 1 week, 1 day ago
FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos

A new vision-language system can turn origami demonstration videos into executable folding programs, using geometry checks and physical simulation to keep the sequence plausible. For game teams, the interesting part …

Research arXiv cs.GR · 2 weeks, 2 days ago
Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations

NeuSOGA turns geometric observations into editable symbolic math, aiming to replace opaque latent encodings with explicit representations. The framework combines topology-guided discovery, Segment Anything-based perception, multi-scale abstraction, and Implicit Area …

Research arXiv cs.GR · 2 weeks, 2 days ago
Endoscopic Depth Estimation Based on Deep Learning: A Survey

Deep-learning depth estimation for endoscopic surgery is getting a broad technical map, with a new survey organizing the field around data, methods, and clinical use. For developers working in medical …

Research arXiv cs.GR · 2 weeks, 2 days ago
Proximity3D: Shape from Capacitive Proximity on Sensing Manifold

A new reconstruction method turns curved capacitive textiles into a 3D shape sensor, letting robots infer nearby geometry from proximity fields instead of flat RGB or depth inputs. Proximity3D aggregates …

Research arXiv cs.GR · 2 weeks, 3 days ago
OpenVX 1.3.2 Released: More Precise Errors, Better Consistency, and Groundwork for 2.0

Khronos has released OpenVX 1.3.2, tightening error reporting and consistency for vision pipelines. The update adds VX_ERROR_TIMEOUT and VX_ERROR_GRAPH_NOT_VERIFIED, expands image support with RGBA and U1 handling, and sets up …

Blog Khronos · 2 weeks, 4 days ago
What Will This Copper Look Like Later? Forecasting Surface Appearance and Rendering It as a PBR Material

A new copper-oxidation pipeline forecasts how a fixed surface will look 10 accelerated units ahead, then turns that prediction into PBR maps for albedo, normal, roughness, and metallic. The practical …

Research arXiv cs.GR · 2 weeks, 4 days ago
A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation

A new framework cuts the cost of building urban segmentation training data by turning rough synthetic scenes into target-aligned images. It adapts an off-the-shelf diffusion model with only imperfect pseudo-labels, …

Research arXiv cs.GR · 3 weeks ago
Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering

A new intrinsic decomposition method tackles a long-standing misattribution problem in point-based 3D scene reconstruction. Intrinsic PAPR replaces translucent volume aggregation with proximity-aware point rendering so each surface point can …

Research arXiv cs.GR · 3 weeks, 2 days ago
EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing

EditStream folds text-to-video, image-to-video, video-to-video, editing propagation, reference-guided edits, and camera pose changes into one DiT-based system. The big shift for developers is its few-step autoregressive streaming setup, aimed at …

Research arXiv cs.GR · 3 weeks, 3 days ago
Page 1 of 11 Next