Skip to main content
GameDev.net gamedev.net

Diffusion News

The latest Diffusion coverage curated for game developers.

Grid-Free Monte Carlo for Time-Dependent Diffusion

Researchers have extended grid-free Monte Carlo diffusion solvers to transient heat equations, removing the need for volumetric meshing and time stepping. The method targets time-dependent diffusion with initial conditions plus …

Research arXiv cs.GR · 1 week, 4 days ago
Multi-Conditioned Diffusion Synthesis of Sand Boils for Low-Resource Earthen-Levee Inspection

A diffusion pipeline is being used to synthesize sand-boil inspection imagery for earthen levees when real defect annotations are scarce. The system fine-tunes Stable Diffusion XL with DreamBooth, then steers …

Research arXiv cs.GR · 2 months, 1 week ago
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation

PixGS pushes 3D Gaussian splat generation into a single-stage, pixel-space diffusion pipeline, aiming to cut the artifacts and error buildup common in latent-based workflows. The method directly denoises splat attributes …

Research arXiv cs.GR · 2 months, 3 weeks ago
Dipole Diffusion Error in Thin Geometry: Optical Thickness Laws for Grid-Free Subsurface Scattering

For graphics programmers working on skin, wax, or other thin translucent materials, this paper puts numbers on a long-standing dipole problem: the geometry error falls like about 1.99e^-2τ for diffuse …

Research arXiv cs.GR · 2 months, 3 weeks ago
HiMat: DiT-based Ultra-High Resolution SVBRDF Generation

HiMat tackles a real bottleneck for material authoring: generating 4K SVBRDFs without blowing up memory or losing map alignment. It uses a high-compression latent space plus a diffusion transformer with …

Research arXiv cs.GR · 3 months, 2 weeks ago
MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer

MeshFlow replaces slow auto-regressive mesh tokenization with a continuous latent VAE plus a rectified-flow transformer, and it claims 18x faster generation than the fastest AR baseline. For graphics and tools …

Research arXiv cs.GR · 3 months, 3 weeks ago
AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization

AvatarMix tackles a real pain point in avatar outfit transfer: keeping identity and clothing intact without seam or intersection artifacts. It composes head and body from two high-fidelity Gaussian avatars, …

Research arXiv cs.GR · 3 months, 3 weeks ago
Sketch2Motion: Text-driven 2D Sketch to 3D Animation via Diffusion-guided Skeleton Optimization

A new paper tackles a hard animation problem: turning a 2D sketch plus text into usable 3D motion without paired motion data. The interesting bit for animation and tech art …

Research arXiv cs.GR · 3 months, 4 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
Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing

A 5D point-cloud garment representation tries to bridge the gap between fast, high-level generation and the messy reality of editing both sewing patterns and draped 3D cloth. For teams working …

Research arXiv cs.GR · 3 months, 4 weeks ago
Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation

A new paper argues that subject-driven image generation works better when the diffusion model is conditioned on a multimodal LLM that sees text and reference images together. The authors also …

Research arXiv cs.GR · 3 months, 4 weeks ago
VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement

For level and tools teams, the interesting bit is the move from loose bounding proxies to explicit voxel occupancy for indoor scene layout. VoxScene claims that this cuts down collisions …

Research arXiv cs.GR · 4 months ago
DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer

A diffusion-based material transfer paper is trying to cut out two common pain points for graphics teams: text prompts and extra reference networks. DealMaTe uses depth, normal, and lighting inputs …

Research arXiv cs.GR · 4 months, 1 week ago
SURF: Signature-Retained Fast Video Generation

SURF tackles a practical bottleneck for teams experimenting with video generation: 720p inference can take 50+ minutes on Wan2.1. The paper’s two-stage approach keeps more of the base model’s layout, …

Research arXiv cs.GR · 6 months ago
DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting

The introduction of DiffusionLight-Turbo offers graphics programmers a significant leap in light probe estimation, reducing processing time from 30 minutes to just 30 seconds. This efficiency gain is achieved with …

Research arXiv cs.GR · 7 months, 3 weeks ago
DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders

DiffusionBrowser introduces a game-changing interactive preview system for video diffusion models, allowing developers to generate previews in real-time. This model-agnostic framework enhances control during the denoising process, making it particularly …

Research arXiv cs.GR · 9 months, 1 week ago
NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation

The introduction of Phase-Preserving Diffusion (?C6-PD) marks a significant advancement in structure-aligned generation, particularly beneficial for graphics programmers and artists. By preserving input phase while randomizing magnitude, this method enhances …

Research arXiv cs.GR · 9 months, 2 weeks ago