Hexels use hexagonal primitives for more efficient 3D scene rendering
Across 34 scenes, Hexels beat memory-matched 2DGS by 4.53-7.38 dB PSNR with lower training VRAM.
Stories per day · 30 days
2 RSS
Relatedcomputer-vision33d-gaussian-splatting2feed-forward23d-reconstruction14d-reconstruction1camera-control1computer-graphics1gaussian-splatting1generative-models1infinisplat1multi-view1positional-encoding1transformers1video-diffusion1
16 stories, newest first · one card per story
Stories tagged #novel-view-synthesis
HRoPE encodes patch surfaces as slanted planes for multi-view attention
Plane parameters need no ground-truth geometry and can be learned from view synthesis alone or taken from foundation models.
FineSplat uses local grouping for detailed 3D Gaussian splats
View-wise and 3D grouping plus rendering-error feedback keep Gaussian counts at or below prior methods.
Holo4D steers video diffusion with reconstructed 4D trajectories
Projected source-view trajectories condition a pretrained video model so unseen regions are filled without retraining the generator.
InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views
InfiniSplat v2 improves feed-forward 3D Gaussian rendering quality across large viewpoint changes.
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
LEGO turns one exocentric video into an egocentric view with a lifting-free synthesizer and diffusion model.
NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis
NAMVIS generates consistent multi-view images with geometry-conditioned autoregression, beating diffusion baselines and running over 3x faster.
Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
SNAP, a self-supervised pose-conditioned transformer for novel view synthesis, learns transferable geometric representations competitive with geometry-supervised methods across five tasks.
DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes
DyRAD renders dynamic radar range-azimuth-Doppler views, recovering 90.7% of RADIal detections versus 26.9%.
GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space
GeoVerse synthesizes world-consistent novel views inside a geometric latent space using video appearance priors.
VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis
VGGT-Diff routes VGGT-Ω geometry latents into a video diffusion model for sparse-view novel view synthesis.
ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos
ClearGS improves 3D Gaussian Splatting from handheld video using reliability weights and in-video restoration.
Geometric Inconsistency Localization in Multi-View Image Sets
DeformView and DEFECt3R localize geometric inconsistencies in wide-baseline multi-view images for forensics.
Hierarchical NeRF with JAX3D for Volumetric Rendering, Novel-View Synthesis, and 3D Reconstruction
MarkTechPost tutorial implements a hierarchical NeRF in JAX using jax3d volume-rendering primitives for novel-view synthesis and 3D reconstruction.
2
3D Point Splatting for mmWave Radar Novel View Synthesis
Researchers propose 3DPS, a differentiable point renderer for mmWave radar novel view synthesis that outperforms optical-NVS baselines by 1.7x-5.2x.
Reflection-aware Generative Novel View Synthesis
Ref-GeNVS is a training-free method for reflection-consistent generative novel view synthesis that treats mirror images as two complementary views.