Skip to main content
GameDev.net gamedev.net

3D Generation News

The latest 3D Generation coverage curated for game developers.

OREO: Fidelity Alignment in 3D Generation via On-the-fly Rendering-Editing Optimization

arXiv cs.GR details OREO, a 3D generation alignment method that uses on-the-fly edited renderings to push models toward more realistic assets. The system feeds refined 2D views back as pseudo-targets, …

Research arXiv cs.GR · 3 hours, 25 minutes ago
ProxyBuild: Text-Guided Structured 3D Building Generation with Mesh-Anchored Procedural Proxies

arXiv cs.GR details ProxyBuild, a text-guided 3D building system that aims to produce editable structures instead of single baked meshes. The method uses mesh-anchored procedural proxies to separate layout prediction …

Research arXiv cs.GR · 3 days, 3 hours ago
KaiNinja: Extending Native 3D Generators to the Part Level

KaiNinja extends native 3D generation from whole objects to editable parts, targeting the pain point of fused meshes that are awkward to rig, simulate, or modify. Built on TRELLIS.2, it …

Research arXiv cs.GR · 1 week, 3 days ago
Grow3D: Hierarchical Next-Scale Octree Prediction for Fast and High-Fidelity 3D Shape Generation

Researchers have introduced Grow3D, a hierarchical octree-based method for generating 3D shapes with higher fidelity and faster inference. The approach predicts the next scale of an octree step by step, …

Research ACM Graphics · 1 week, 4 days ago
SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image

SNAP3D tackles a common failure mode in part-aware 3D generation: parts that look right but cannot actually assemble. The system uses physics feedback to reduce interpenetration, infer contact relationships, and …

Research arXiv cs.GR · 1 week, 4 days ago
Luce: Relightable Gaussians for 3D Asset Generation

Luce is a new single-image-to-3D pipeline built around relightable Gaussian assets, aiming to preserve geometry, materials, and fine surface detail in one representation. It targets PBR-ready output with albedo, metallic-roughness, …

Research arXiv cs.GR · 4 weeks, 2 days ago
MultiCube: Compositional 3D Generation With Part-Level Semantic and Spatial Control

arXiv cs.GR details MultiCube, a 3D generation method that gives creators part-level control over both meaning and placement. It builds compositional meshes from a text prompt, a part schema, and …

Research arXiv cs.GR · 1 month ago
aDSL: Agentic 3D Creation via Joint Agent-Program Design

A new 3D creation pipeline pairs a custom DSL with a multi-agent LLM workflow to make programmatic content generation less brittle. The system replaces fragile absolute coordinates with relational operators, …

Research arXiv cs.GR · 1 month ago
MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling

MegaParts pushes part-aware 3D generation to 300 parts by pairing an autoregressive model with a token-efficient VQ shape tokenizer. For game teams, the practical angle is finer control over complex …

Research arXiv cs.GR · 1 month, 1 week ago
SCULPT: Subtractive Composition for 3D Part Generation

A new 3D generation method called SCULPT uses subtractive composition to split complete objects into editable parts while keeping the whole coherent. It targets the usual failure modes of part-aware …

Research arXiv cs.GR · 1 month, 1 week ago
PartMat: Material-Aware 3D Part Decomposition with a Single Global Latent

A new 3D decomposition pipeline aims to split objects by material boundaries instead of just functional parts. PartMat uses a single global latent to decode all parts in one pass, …

Research arXiv cs.GR · 1 month, 3 weeks ago
Nova3D: Code-Native Generation of Programmable 3D Assets

Nova3D turns 3D asset generation into executable Blender code instead of a sealed mesh. The system produced valid outputs for all 54 benchmark items, with named parts, assembly trees, numeric …

Research arXiv cs.GR · 1 month, 4 weeks ago
3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects

A new benchmark, 3D-DefectBench, tests how well vision-language models catch fine-grained defects in generated 3D assets. Across 84 pipeline designs and about 3.2 million defect judgments, model choice mattered most, …

Research arXiv cs.GR · 2 months, 1 week ago
CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-Centric 3D Scene Generation

CGGS tackles a stubborn text-to-3D problem: ego-centric scenes that drift in viewpoint and geometry. The pipeline combines a consistency-augmented multi-view diffusion stage, depth from optical flow and point tracks, and …

Research arXiv cs.GR · 2 months, 2 weeks ago
3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling

A new 3D generative modeling framework uses concept bottlenecks to make geometry models more interpretable and steerable. In a proof-of-concept part-manipulation test, it reached 88.8% concept prediction accuracy and a …

Research arXiv cs.GR · 3 months, 2 weeks ago
SymTRELLIS: Symmetry-Enforced Voxel Latents for 3D Generation

A new 3D generation method enforces symmetry directly in the latent/ODE loop, which is the part that matters if you need mechanically plausible assets. SymTRELLIS can handle arbitrary finite point …

Research arXiv cs.GR · 3 months, 3 weeks ago
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation

arXiv cs.GR details SuperVoxelGPT, a 3D tokenization scheme that aims to make autoregressive shape generation faster and more stable. By using adaptive, ordered supervoxels instead of uniform grids, it cuts …

Research arXiv cs.GR · 3 months, 3 weeks ago
Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generation

A new diffusion framework can learn fine-grained object parts from ordinary 2D images, then let you swap, interpolate, and recombine those parts without 3D scans or camera poses. For teams …

Research arXiv cs.GR · 3 months, 4 weeks ago
AnySurf: Any Surface Generation with Directed Edge

A new surface-generation model claims to handle open, closed, and hybrid meshes in one pipeline, which is more relevant than it sounds for character and prop work. The big practical …

Research arXiv cs.GR · 3 months, 4 weeks ago
ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation

ROAR-3D upgrades a pretrained single-view 3D generator to take 1 to 12+ unposed images without the usual fixed-camera setup. The interesting bit for graphics teams is that it routes each …

Research arXiv cs.GR · 4 months ago
Page 1 of 2 Next