REVIEW 14 cited by
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent works show promising results by simply fine-tuning T2I diffusion models for dense perception tasks. However, several crucial design decisions in this process still lack comprehensive justification, encompassing the necessity of the multi-step stochastic diffusion mechanism, training strategy, inference ensemble strategy, and fine-tuning data quality. In this work, we conduct a thorough investigation into critical factors that affect transfer efficiency and performance when using diffusion priors. Our key findings are: 1) High-quality fine-tuning data is paramount for both semantic and geometry perception tasks. 2) The stochastic nature of diffusion models has a slightly negative impact on deterministic visual perception tasks. 3) Apart from fine-tuning the diffusion model with only latent space supervision, task-specific image-level supervision is beneficial to enhance fine-grained details. These observations culminate in the development of GenPercept, an effective deterministic one-step fine-tuning paradigm tailed for dense visual perception tasks. Different from the previous multi-step methods, our paradigm has a much faster inference speed, and can be seamlessly integrated with customized perception decoders and loss functions for image-level supervision, which is critical to improving the fine-grained details of predictions. Comprehensive experiments on diverse dense visual perceptual tasks, including monocular depth estimation, surface normal estimation, image segmentation, and matting, are performed to demonstrate the remarkable adaptability and effectiveness of our proposed method.
Forward citations
Cited by 14 Pith papers
-
Unified Video Dense Prediction from Disjoint Data
A single video backbone predicts eight dense scene tasks from separate single-task datasets via latent distillation from diffusion-based specialists, with no co-annotated data or pseudo-labels.
-
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 perspectiv...
-
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.
-
Video Generation Models are General-Purpose Vision Learners
A video-diffusion backbone fine-tuned as a single-step multi-task perceiver matches or beats specialists on depth, normals, pose and segmentation, with high data efficiency and sim-to-real transfer.
-
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.
-
LuxDiT: Lighting Estimation with Video Diffusion Transformer
A video diffusion transformer fine-tuned on synthetic and real data predicts HDR environment maps from images/videos, cutting peak light-direction error by roughly 45% on sunny outdoor scenes versus DiffusionLight.
-
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.
-
SDMatte: Grafting Diffusion Models for Interactive Matting
SDMatte adapts Stable Diffusion to interactive matting via visual-prompt cross-attention, opacity/coordinate embeddings, and masked self-attention, reporting SOTA results on multiple benchmarks.
-
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.
-
FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal
A coarse-to-fine diffusion SIRR method gates ControlNet residuals with a VLM intensity prior times a multi-scale high-frequency prior, then refines geometry and detail in image space.
-
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...
Discussion (0). Sign in to comment.