Structural Energy-Guided Sampling for View-Consistent Text-to-3D
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.
Code (0)
등록된 구현이 없습니다.
Tasks
3D GenerationSimilar Papers 제목 키워드 기반
Structural Energy Guidance for View-Consistent Text-to-3D Generation
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 GenerationLUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction
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
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 PredictionEnergy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
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
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…