paper-with-me

Papers

Structural Energy-Guided Sampling for View-Consistent Text-to-3D

2025-08-23 · Qing Zhang, Jinguang Tong, Jie Hong, Jing Zhang, Xuesong Li arxiv

Text-to-3D generation often suffers from the Janus problem, where objects look correct from the front but collapse into duplicated or distorted geometry from other angles. We attribute this failure to viewpoint bias in 2D diffusion priors, which propagates into 3D optimization. To address this, we propose Structural Energy-Guided Sampling (SEGS), a training-free, plug-and-play framework that enforces multi-view consistency entirely at sampling time. SEGS defines a structural energy in a PCA subspace of intermediate U-Net features and injects its gradients into the denoising trajectory, steering geometry toward the intended viewpoint while preserving appearance fidelity. Integrated seamlessly into SDS/VSD pipelines, SEGS significantly reduces Janus artifacts, achieving improved geometric alignment and viewpoint consistency without retraining or weight modification.

📄 PDF Abstract BibTeX arXiv:2508.16917

Code (0)

등록된 구현이 없습니다.

Tasks

3D Generation

Similar Papers 제목 키워드 기반

Structural Energy Guidance for View-Consistent Text-to-3D Generation

2026-05-19 · Qing Zhang, Jinguang Tong, Jing Zhang, Jie Hong 외 arxiv

Text-to-3D generation based on diffusion models often suffers from the Janus problem, leading to inconsistent geometry across viewpoints. This work identifies viewpoint bias in 2D diffusion priors as the main cause and p…

3D Generation

LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction

2026-06-15 · Jigang Duan, Jiayi Wang, Heran Wang, Ping Yang 외 arxiv

Sparse-view CT reduces radiation dose and scanning time by acquiring fewer projection views, but angular undersampling makes reconstruction severely ill-posed, causing streak artifacts, structural blurring, and loss of f…

Energy-Balanced Hyperspherical Graph Representation Learning via Structural Binding and Entropic Dispersion

2025-12-30 · Rui Chen, Junjun Guo, Hongbin Wang, Yan Xiang 외 arxiv

Graph Representation Learning (GRL) can be fundamentally modeled as a physical process of seeking an energy equilibrium state for a node system on a latent manifold. However, existing Graph Neural Networks (GNNs) often s…

Graph Representation LearningNode ClassificationLink Prediction

Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery

2025-12-27 · Guikun Xu, Xiaohan Yi, Ziqiao Meng, Peilin Zhao 외 arxiv

Exploring molecular energy landscapes and identifying ground-state conformations are central challenges in computational chemistry. However, generating diverse low-energy conformers from molecular graphs remains expensiv…

Colored Noise Diffusion Sampling

2026-05-28 · Hadar Davidson, Noam Issachar, Sagie Benaim arxiv

Diffusion models achieve state-of-the-art image synthesis, with their generative trajectories fundamentally exhibiting a spectral bias, resolving low-frequency global structures early and high-frequency fine details late…