Papers › ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and...

ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian Splatting

10 Apr 2025arXiv:2504.08100archive 2025-07-28

Junbang Liu, Enpei Huang, Dongxing Mao, HUI ZHANG, Xinyuan Song, Yongxin Ni

Creating 3D content from single-view images is a challenging problem that has attracted considerable attention in recent years. Current approaches typically utilize score distillation sampling (SDS) from pre-trained 2D diffusion models to generate multi-view 3D representations. Although some methods have made notable progress by balancing generation speed and model quality, their performance is often limited by the visual inconsistencies of the diffusion model outputs. In this work, we propose ContrastiveGaussian, which integrates contrastive learning into the generative process. By using a perceptual loss, we effectively differentiate between positive and negative samples, leveraging the visual inconsistencies to improve 3D generation quality. To further enhance sample differentiation and improve contrastive learning, we incorporate a super-resolution model and introduce another Quantity-Aware Triplet Loss to address varying sample distributions during training. Our experiments demonstrate that our approach achieves superior texture fidelity and improved geometric consistency.

PaperPDFCode

Code

yanllan-ljb/contrastivegaussian officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D GenerationContrastive LearningSuper-Resolution

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionContrastive LearningDiffusionSPEEDSoftmaxTriplet Loss

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections