REVIEW 6 cited by
MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
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
This paper presents a neural architecture MVDiffusion++ for 3D object reconstruction that synthesizes dense and high-resolution views of an object given one or a few images without camera poses. MVDiffusion++ achieves superior flexibility and scalability with two surprisingly simple ideas: 1) A ``pose-free architecture'' where standard self-attention among 2D latent features learns 3D consistency across an arbitrary number of conditional and generation views without explicitly using camera pose information; and 2) A ``view dropout strategy'' that discards a substantial number of output views during training, which reduces the training-time memory footprint and enables dense and high-resolution view synthesis at test time. We use the Objaverse for training and the Google Scanned Objects for evaluation with standard novel view synthesis and 3D reconstruction metrics, where MVDiffusion++ significantly outperforms the current state of the arts. We also demonstrate a text-to-3D application example by combining MVDiffusion++ with a text-to-image generative model. The project page is at https://mvdiffusion-plusplus.github.io.
Forward citations
Cited by 6 Pith papers
-
PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
A multi-view diffusion pipeline that segments 3D objects into parts, completes occluded or invisible parts, and reconstructs them into a compositional 3D asset.
-
LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors
LiftImage3D generates small-motion video clips from one image, registers them with MASt3R, and fits a distortion-aware 3D Gaussian field whose canonical scene renders new views.
-
CheapNVS: Real-Time On-Device Narrow-Baseline Novel View Synthesis
CheapNVS performs narrow-baseline single-view novel view synthesis on mobile devices by learning warping and inpainting in parallel from a shared latent space.
-
UnCommon Objects in 3D
uCO3D is a large, diverse, high-quality real-object video dataset with 3D annotations that improves training of feedforward 3D reconstruction and text-to-3D models.
-
Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views
Pragmatist turns sparse unposed photos of an object into a high-fidelity 3D mesh by generating consistent canonical views with a diffusion model, reconstructing a triplane mesh, then refining camera poses and texture ...
-
Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds
A texture-generation pipeline that produces 1024x1024 textures from text in 3.07 seconds on an H100, with quality comparable to SyncMVD and other prior methods.
Discussion (0). Continue with ORCID to comment.