MV-SDI aggregates K-view gradients per step via accumulation and antithetic pairs at fixed UNet budget, raising CLIP R-Precision from 74.8% to 83.8% (K=2) and halving steps while keeping the 2D prior frozen.
Re- imagine the negative prompt algorithm: Transform 2d diffusion into 3d, alleviate janus problem and beyond
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
verdicts
UNVERDICTED 10representative citing papers
Camera-Relative Object Coordinates (CROCS) as an intermediate geometry representation in two-stage image-to-3D models yields superior novel-view quality, geometric accuracy, and multiview consistency over depth maps, visual features, and other pointmap alternatives.
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
Probability-Flow Distillation exactly matches the Wasserstein gradient flow of the target distribution when distilling 2D diffusion priors into 3D models, yielding higher-fidelity results than SDS or SDI.
A training-free framework uses physics-violating counterfactual prompts and Synchronized Decoupled Guidance to suppress implausible motions in diffusion-based video generation while preserving photorealism.
SyncDreamer produces multiview-consistent images from a single input image by jointly modeling their distribution and synchronizing intermediate diffusion states via 3D-aware attention.
ByG enables unpaired training of flow matching editing models by pairing self-extracted instruction-following cues with cycle-consistency and routing gradients from clean predictions to noisy states.
SEGS constructs structural energy in the PCA subspace of U-Net features and injects its gradient into the denoising process to improve multi-view consistency in text-to-3D generation.
EmDT combines UMAP clustering with a Transformer-based diffusion process to create synthetic fraud samples that improve XGBoost classification on credit card fraud data while preserving correlations and privacy.
ConsDreamer refines conditional and unconditional terms in score distillation via view disentanglement and geometric consistency loss to reduce the Janus problem in zero-shot text-to-3D.
citing papers explorer
-
Variance Reduction on the Camera Axis: Multi-View Score Distillation for 3D
MV-SDI aggregates K-view gradients per step via accumulation and antithetic pairs at fixed UNet budget, raising CLIP R-Precision from 74.8% to 83.8% (K=2) and halving steps while keeping the 2D prior frozen.
-
How to Spin an Object: First, Get the Shape Right
Camera-Relative Object Coordinates (CROCS) as an intermediate geometry representation in two-stage image-to-3D models yields superior novel-view quality, geometric accuracy, and multiview consistency over depth maps, visual features, and other pointmap alternatives.
-
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
-
Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation
Probability-Flow Distillation exactly matches the Wasserstein gradient flow of the target distribution when distilling 2D diffusion priors into 3D models, yielding higher-fidelity results than SDS or SDI.
-
Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility
A training-free framework uses physics-violating counterfactual prompts and Synchronized Decoupled Guidance to suppress implausible motions in diffusion-based video generation while preserving photorealism.
-
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
SyncDreamer produces multiview-consistent images from a single input image by jointly modeling their distribution and synchronizing intermediate diffusion states via 3D-aware attention.
-
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching
ByG enables unpaired training of flow matching editing models by pairing self-extracted instruction-following cues with cycle-consistency and routing gradients from clean predictions to noisy states.
-
Structural Energy Guidance for View-Consistent Text-to-3D Generation
SEGS constructs structural energy in the PCA subspace of U-Net features and injects its gradient into the denoising process to improve multi-view consistency in text-to-3D generation.
-
EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detection
EmDT combines UMAP clustering with a Transformer-based diffusion process to create synthetic fraud samples that improve XGBoost classification on credit card fraud data while preserving correlations and privacy.
-
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
ConsDreamer refines conditional and unconditional terms in score distillation via view disentanglement and geometric consistency loss to reduce the Janus problem in zero-shot text-to-3D.