MUSE shows that the native timestep embedding in diffusion models acts as a parameter-free steering signal for multi-task monocular depth and normal estimation via manifold decoupling in latent space.
What matters when repurposing diffusion models for general dense perception tasks?
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 9verdicts
UNVERDICTED 9roles
background 1polarities
unclear 1representative citing papers
DepthMaster unifies metric monocular depth estimation for perspective and panoramic images by patching panoramas into perspective views, adding a consistency loss and virtual cameras, and training mostly on perspective data to reach SOTA zero-shot results on 13 datasets.
LAGRNet embeds learnable algebraic group, ring, and sheaf structures into a neural network to improve accuracy and generalization in monocular depth estimation.
CDPR integrates polarization priors into a diffusion-based monocular depth estimator via shared latent space and adaptive gating, outperforming RGB-only methods in challenging scenes.
UniGP unifies controllable generation and dense prediction in an MMDiT-based diffusion model through simple joint training that preserves backbone priors.
UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.
Ouroboros uses two single-step diffusion models with cycle consistency for forward and inverse rendering, extending intrinsic decomposition to indoor/outdoor scenes with faster inference than multi-step methods.
Depth Anything V2 delivers finer, more robust monocular depth predictions by replacing real labeled images with synthetic data, scaling the teacher model, and using large-scale pseudo-labeled real images for student training.
DepthMaster proposes a single-step diffusion model with Feature Alignment and Fourier Enhancement modules in a two-stage training process to improve generalization and detail preservation in monocular depth estimation over prior diffusion methods.
citing papers explorer
-
MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction
MUSE shows that the native timestep embedding in diffusion models acts as a parameter-free steering signal for multi-task monocular depth and normal estimation via manifold decoupling in latent space.
-
DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images
DepthMaster unifies metric monocular depth estimation for perspective and panoramic images by patching panoramas into perspective views, adding a consistency loss and virtual cameras, and training mostly on perspective data to reach SOTA zero-shot results on 13 datasets.
-
Monocular Depth Estimation via Neural Network with Learnable Algebraic Group and Ring Structures
LAGRNet embeds learnable algebraic group, ring, and sheaf structures into a neural network to improve accuracy and generalization in monocular depth estimation.
-
CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation
CDPR integrates polarization priors into a diffusion-based monocular depth estimator via shared latent space and adaptive gating, outperforming RGB-only methods in challenging scenes.
-
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
UniGP unifies controllable generation and dense prediction in an MMDiT-based diffusion model through simple joint training that preserves backbone priors.
-
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.
-
Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering
Ouroboros uses two single-step diffusion models with cycle consistency for forward and inverse rendering, extending intrinsic decomposition to indoor/outdoor scenes with faster inference than multi-step methods.
-
Depth Anything V2
Depth Anything V2 delivers finer, more robust monocular depth predictions by replacing real labeled images with synthetic data, scaling the teacher model, and using large-scale pseudo-labeled real images for student training.
-
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation
DepthMaster proposes a single-step diffusion model with Feature Alignment and Fourier Enhancement modules in a two-stage training process to improve generalization and detail preservation in monocular depth estimation over prior diffusion methods.