Pith. sign in

REVIEW 7 cited by

3D generation on ImageNet

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

arxiv 2303.01416 v1 pith:57ERPCCC submitted 2023-03-02 cs.CV cs.AIcs.GR

classification cs.CVcs.AIcs.GR
keywords datasetstrainingx256cameraimagenetmodeldepthexisting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the scene. This makes them inapplicable to diverse, in-the-wild datasets of non-alignable scenes rendered from arbitrary camera poses. In this work, we develop a 3D generator with Generic Priors (3DGP): a 3D synthesis framework with more general assumptions about the training data, and show that it scales to very challenging datasets, like ImageNet. Our model is based on three new ideas. First, we incorporate an inaccurate off-the-shelf depth estimator into 3D GAN training via a special depth adaptation module to handle the imprecision. Then, we create a flexible camera model and a regularization strategy for it to learn its distribution parameters during training. Finally, we extend the recent ideas of transferring knowledge from pre-trained classifiers into GANs for patch-wise trained models by employing a simple distillation-based technique on top of the discriminator. It achieves more stable training than the existing methods and speeds up the convergence by at least 40%. We explore our model on four datasets: SDIP Dogs 256x256, SDIP Elephants 256x256, LSUN Horses 256x256, and ImageNet 256x256, and demonstrate that 3DGP outperforms the recent state-of-the-art in terms of both texture and geometry quality. Code and visualizations: https://snap-research.github.io/3dgp.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    HeadsUp maps multi-view captures to UV-parameterized 3D Gaussians on a template via an encoder-decoder, achieving state-of-the-art quality and generalization after training on more than 10,000 subjects.

  2. Structured 3D Latents for Scalable and Versatile 3D Generation

    cs.CV 2024-12 unverdicted novelty 7.0 of 10

    SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.

  3. AIMold: An Autonomous AI-based Pipeline for Complex Mold Design

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A new dataset and deep learning pipeline generate upper and lower molds, parting surfaces, and auxiliary components for complex injection-molded parts.

  4. Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A video-to-4D model that encodes mesh animations into compact Gaussian variation latents and diffuses them conditioned on the video and a canonical Gaussian splat.

  5. SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

    cs.CV 2023-09 unverdicted novelty 6.0 of 10

    SyncDreamer produces multiview-consistent images from a single input image by jointly modeling their distribution and synchronizing intermediate diffusion states via 3D-aware attention.

  6. Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    Pith review generated a malformed one-line summary.

  7. Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    HeadsUp reconstructs high-quality 3D Gaussian heads from multi-view images via an encoder-decoder outputting UV-parameterized Gaussians on a neutral template, trained on over 10,000 subjects for generalization and dow...

Pith tools