Phased Consistency Model

The consistency model (CM) has recently made significant progress in accelerating the generation of diffusion models. However, its application to high-resolution, text-conditioned image generation in the latent space (a.k.a., LCM) remains unsatisfactory. In this paper, we identify three key flaws in the current design of LCM. We investigate the reasons behind these limitations and propose the Phased Consistency Model (PCM), which generalizes the design space and addresses all identified limitations. Our evaluations demonstrate that PCM significantly outperforms LCM across 1--16 step generation settings. While PCM is specifically designed for multi-step refinement, it achieves even superior or comparable 1-step generation results to previously state-of-the-art specifically designed 1-step methods. Furthermore, we show that PCM's methodology is versatile and applicable to video generation, enabling us to train the state-of-the-art few-step text-to-video generator. More details are available at https://g-u-n.github.io/projects/pcm/.

Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models

Optimizing a text-to-image diffusion model with a given reward function is an important but underexplored research area. In this study, we propose Deep Reward Tuning (DRTune), an algorithm that directly supervises the final output image of a text-to-image diffusion model and back-propagates through the iterative sampling process to the input noise. We find that training earlier steps in the sampling process is crucial for low-level rewards, and deep supervision can be achieved efficiently and effectively by stopping the gradient of the denoising network input. DRTune is extensively evaluated on various reward models. It consistently outperforms other algorithms, particularly for low-level control signals, where all shallow supervision methods fail. Additionally, we fine-tune Stable Diffusion XL 1.0 (SDXL 1.0) model via DRTune to optimize Human Preference Score v2.1, resulting in the Favorable Diffusion XL 1.0 (FDXL 1.0) model. FDXL 1.0 significantly enhances image quality compared to SDXL 1.0 and reaches comparable quality compared with Midjourney v5.2.

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

Video outpainting is a challenging task, aiming at generating video content outside the viewport of the input video while maintaining inter-frame and intra-frame consistency. Existing methods fall short in either generation quality or flexibility. We introduce MOTIA Mastering Video Outpainting Through Input-Specific Adaptation, a diffusion-based pipeline that leverages both the intrinsic data-specific patterns of the source video and the image/video generative prior for effective outpainting. MOTIA comprises two main phases: input-specific adaptation and pattern-aware outpainting. The input-specific adaptation phase involves conducting efficient and effective pseudo outpainting learning on the single-shot source video. This process encourages the model to identify and learn patterns within the source video, as well as bridging the gap between standard generative processes and outpainting. The subsequent phase, pattern-aware outpainting, is dedicated to the generalization of these learned patterns to generate outpainting outcomes. Additional strategies including spatial-aware insertion and noise travel are proposed to better leverage the diffusion model's generative prior and the acquired video patterns from source videos. Extensive evaluations underscore MOTIA's superiority, outperforming existing state-of-the-art methods in widely recognized benchmarks. Notably, these advancements are achieved without necessitating extensive, task-specific tuning.

AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning

Video diffusion models has been gaining increasing attention for its ability to produce videos that are both coherent and of high fidelity. However, the iterative denoising process makes it computationally intensive and time-consuming, thus limiting its applications. Inspired by the Consistency Model (CM) that distills pretrained image diffusion models to accelerate the sampling with minimal steps and its successful extension Latent Consistency Model (LCM) on conditional image generation, we propose AnimateLCM, allowing for high-fidelity video generation within minimal steps. Instead of directly conducting consistency learning on the raw video dataset, we propose a decoupled consistency learning strategy that decouples the distillation of image generation priors and motion generation priors, which improves the training efficiency and enhance the generation visual quality. Additionally, to enable the combination of plug-and-play adapters in stable diffusion community to achieve various functions (e.g., ControlNet for controllable generation). we propose an efficient strategy to adapt existing adapters to our distilled text-conditioned video consistency model or train adapters from scratch without harming the sampling speed. We validate the proposed strategy in image-conditioned video generation and layout-conditioned video generation, all achieving top-performing results. Experimental results validate the effectiveness of our proposed method. Code and weights will be made public. More details are available at https://github.com/G-U-N/AnimateLCM.

Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling

We introduce Motion-I2V, a novel framework for consistent and controllable image-to-video generation (I2V). In contrast to previous methods that directly learn the complicated image-to-video mapping, Motion-I2V factorizes I2V into two stages with explicit motion modeling. For the first stage, we propose a diffusion-based motion field predictor, which focuses on deducing the trajectories of the reference image's pixels. For the second stage, we propose motion-augmented temporal attention to enhance the limited 1-D temporal attention in video latent diffusion models. This module can effectively propagate reference image's feature to synthesized frames with the guidance of predicted trajectories from the first stage. Compared with existing methods, Motion-I2V can generate more consistent videos even at the presence of large motion and viewpoint variation. By training a sparse trajectory ControlNet for the first stage, Motion-I2V can support users to precisely control motion trajectories and motion regions with sparse trajectory and region annotations. This offers more controllability of the I2V process than solely relying on textual instructions. Additionally, Motion-I2V's second stage naturally supports zero-shot video-to-video translation. Both qualitative and quantitative comparisons demonstrate the advantages of Motion-I2V over prior approaches in consistent and controllable image-to-video generation. Please see our project page at https://xiaoyushi97.github.io/Motion-I2V/.

InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation

Empowering models to dynamically accomplish tasks specified through natural language instructions represents a promising path toward more capable and general artificial intelligence. In this work, we introduce InstructSeq, an instruction-conditioned multi-modal modeling framework that unifies diverse vision tasks through flexible natural language control and handling of both visual and textual data. InstructSeq employs a multimodal transformer architecture encompassing visual, language, and sequential modeling. We utilize a visual encoder to extract image features and a text encoder to encode instructions. An autoregressive transformer fuses the representations and generates sequential task outputs. By training with LLM-generated natural language instructions, InstructSeq acquires a strong comprehension of free-form instructions for specifying visual tasks. This provides an intuitive interface for directing capabilities using flexible natural instructions. Without any task-specific tuning, InstructSeq achieves compelling performance on semantic segmentation, referring expression segmentation/comprehension, and image captioning. The flexible control and multi-task unification empower the model with more human-like versatility and generalizability for computer vision. The code will be released soon at https://github.com/rongyaofang/InstructSeq.

DiffRoom: Diffusion-based High-Quality 3D Room Reconstruction and Generation with Occupancy Prior

We present DiffRoom, a novel framework for tackling the problem of high-quality 3D indoor room reconstruction and generation, both of which are challenging due to the complexity and diversity of the room geometry. Although diffusion-based generative models have previously demonstrated impressive performance in image generation and object-level 3D generation, they have not yet been applied to room-level 3D generation due to their computationally intensive costs. In DiffRoom, we propose a sparse 3D diffusion network that is efficient and possesses strong generative performance for Truncated Signed Distance Field (TSDF), based on a rough occupancy prior. Inspired by KinectFusion's incremental alignment and fusion of local SDFs, we propose a diffusion-based TSDF fusion approach that iteratively diffuses and fuses TSDFs, facilitating the reconstruction and generation of an entire room environment. Additionally, to ease training, we introduce a curriculum diffusion learning paradigm that speeds up the training convergence process and enables high-quality reconstruction. According to the user study, the mesh quality generated by our DiffRoom can even outperform the ground truth mesh provided by ScanNet. Please visit our project page for the latest progress and demonstrations: https://akirahero.github.io/DiffRoom/.

FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow

This paper introduces a novel transformer-based network architecture, FlowFormer, along with the Masked Cost Volume AutoEncoding (MCVA) for pretraining it to tackle the problem of optical flow estimation. FlowFormer tokenizes the 4D cost-volume built from the source-target image pair and iteratively refines flow estimation with a cost-volume encoder-decoder architecture. The cost-volume encoder derives a cost memory with alternate-group transformer~(AGT) layers in a latent space and the decoder recurrently decodes flow from the cost memory with dynamic positional cost queries. On the Sintel benchmark, FlowFormer architecture achieves 1.16 and 2.09 average end-point-error~(AEPE) on the clean and final pass, a 16.5\% and 15.5\% error reduction from the GMA~(1.388 and 2.47). MCVA enhances FlowFormer by pretraining the cost-volume encoder with a masked autoencoding scheme, which further unleashes the capability of FlowFormer with unlabeled data. This is especially critical in optical flow estimation because ground truth flows are more expensive to acquire than labels in other vision tasks. MCVA improves FlowFormer all-sided and FlowFormer+MCVA ranks 1st among all published methods on both Sintel and KITTI-2015 benchmarks and achieves the best generalization performance. Specifically, FlowFormer+MCVA achieves 1.07 and 1.94 AEPE on the Sintel benchmark, leading to 7.76\% and 7.18\% error reductions from FlowFormer.

Context-TAP: Tracking Any Point Demands Spatial Context Features

We tackle the problem of Tracking Any Point (TAP) in videos, which specifically aims at estimating persistent long-term trajectories of query points in videos. Previous methods attempted to estimate these trajectories independently to incorporate longer image sequences, therefore, ignoring the potential benefits of incorporating spatial context features. We argue that independent video point tracking also demands spatial context features. To this end, we propose a novel framework Context-TAP, which effectively improves point trajectory accuracy by aggregating spatial context features in videos. Context-TAP contains two main modules: 1) a SOurse Feature Enhancement (SOFE) module, and 2) a TArget Feature Aggregation (TAFA) module. Context-TAP significantly improves PIPs all-sided, reducing 11.4% Average Trajectory Error of Occluded Points (ATE-Occ) on CroHD and increasing 11.8% Average Percentage of Correct Keypoint (A-PCK) on TAP-Vid-Kinectics. Demos are available at this $\href{https://wkbian.github.io/Projects/Context-TAP/}{webpage}$.

PATS: Patch Area Transportation with Subdivision for Local Feature Matching

Local feature matching aims at establishing sparse correspondences between a pair of images. Recently, detector-free methods present generally better performance but are not satisfactory in image pairs with large scale differences. In this paper, we propose Patch Area Transportation with Subdivision (PATS) to tackle this issue. Instead of building an expensive image pyramid, we start by splitting the original image pair into equal-sized patches and gradually resizing and subdividing them into smaller patches with the same scale. However, estimating scale differences between these patches is non-trivial since the scale differences are determined by both relative camera poses and scene structures, and thus spatially varying over image pairs. Moreover, it is hard to obtain the ground truth for real scenes. To this end, we propose patch area transportation, which enables learning scale differences in a self-supervised manner. In contrast to bipartite graph matching, which only handles one-to-one matching, our patch area transportation can deal with many-to-many relationships. PATS improves both matching accuracy and coverage, and shows superior performance in downstream tasks, such as relative pose estimation, visual localization, and optical flow estimation. The source code is available at \url{https://zju3dv.github.io/pats/}.