CVPR 2024 Papers

The remarkable efficacy of text-to-image diffusion models has motivated extensive exploration of their potential application in video domains. Zero-shot methods seek to extend image diffusion models to videos without necessitating model training. Recent methods mainly focus on incorporating inter-frame correspondence into attention mechanisms. However the soft constraint imposed on determining where to attend to valid features can sometimes be insufficient resulting in temporal inconsistency. In this paper we introduce FRESCO intra-frame correspondence alongside inter-frame correspondence to establish a more robust spatial-temporal constraint. This enhancement ensures a more consistent transformation of semantically similar content across frames. Beyond mere attention guidance our approach involves an explicit update of features to achieve high spatial-temporal consistency with the input video significantly improving the visual coherence of the resulting translated videos. Extensive experiments demonstrate the effectiveness of our proposed framework in producing high-quality coherent videos marking a notable improvement over existing zero-shot methods.

The vision and language generative models have been overgrown in recent years. For video generation various open-sourced models and public-available services have been developed to generate high-quality videos. However these methods often use a few metrics e.g. FVD or IS to evaluate the performance. We argue that it is hard to judge the large conditional generative models from the simple metrics since these models are often trained on very large datasets with multi-aspect abilities. Thus we propose a novel framework and pipeline for exhaustively evaluating the performance of the generated videos. Our approach involves generating a diverse and comprehensive list of 700 prompts for text-to-video generation which is based on an analysis of real-world user data and generated with the assistance of a large language model. Then we evaluate the state-of-the-art video generative models on our carefully designed benchmark in terms of visual qualities content qualities motion qualities and text-video alignment with 17 well-selected objective metrics. To obtain the final leaderboard of the models we further fit a series of coefficients to align the objective metrics to the users' opinions. Based on the proposed human alignment method our final score shows a higher correlation than simply averaging the metrics showing the effectiveness of the proposed evaluation method.

In video super-resolution it is common to use a frame-wise alignment to support the propagation of information over time. The role of alignment is well-studied for low-level enhancement in video but existing works overlook a critical step -- resampling. We show through extensive experiments that for alignment to be effective the resampling should preserve the reference frequency spectrum while minimizing spatial distortions. However most existing works simply use a default choice of bilinear interpolation for resampling even though bilinear interpolation has a smoothing effect and hinders super-resolution. From these observations we propose an implicit resampling-based alignment. The sampling positions are encoded by a sinusoidal positional encoding while the value is estimated with a coordinate network and a window-based cross-attention. We show that bilinear interpolation inherently attenuates high-frequency information while an MLP-based coordinate network can approximate more frequencies. Experiments on synthetic and real-world datasets show that alignment with our proposed implicit resampling enhances the performance of state-of-the-art frameworks with minimal impact on both compute and parameters.

Extending large image-text pre-trained models (e.g. CLIP) for video understanding has made significant advancements. To enable the capability of CLIP to perceive dynamic information in videos existing works are dedicated to equipping the visual encoder with various temporal modules. However these methods exhibit "asymmetry" between the visual and textual sides with neither temporal descriptions in input texts nor temporal modules in text encoder. This limitation hinders the potential of language supervision emphasized in CLIP and restricts the learning of temporal features as the text encoder has demonstrated limited proficiency in motion understanding. To address this issue we propose leveraging "MoTion-Enhanced Descriptions" (MoTED) to facilitate the extraction of distinctive temporal features in videos. Specifically we first generate discriminative motion-related descriptions via querying GPT-4 to compare easy-confusing action categories. Then we incorporate both the visual and textual encoders with additional perception modules to process the video frames and generated descriptions respectively. Finally we adopt a contrastive loss to align the visual and textual motion features. Extensive experiments on five benchmarks show that MoTED surpasses state-of-the-art methods with convincing gaps laying a solid foundation for empowering CLIP with strong temporal modeling.

Recent years have witnessed remarkable progress in image generation task where users can create visually astonishing images with high-quality. However exsiting text-to-image diffusion models are proficient in generating concrete concepts (dogs) but encounter challenges with more abstract ones (emotions). Several efforts have been made to modify image emotions with color and style adjustments facing limitations in effectively conveying emotions with fixed image contents. In this work we introduce Emotional Image Content Generation (EIGC) a new task to generate semantic-clear and emotion-faithful images given emotion categories. Specifically we propose an emotion space and construct a mapping network to align it with powerful Contrastive Language-Image Pre-training (CLIP) space providing a concrete interpretation of abstract emotions. Attribute loss and emotion confidence are further proposed to ensure the semantic diversity and emotion fidelity of the generated images. Our method outperforms the state-the-art text-to-image approaches both quantitatively and qualitatively where we derive three custom metrics i.e.emotion accuracy semantic clarity and semantic diversity. In addition to generation our method can help emotion understanding and inspire emotional art design. Project page: https://vcc.tech/research/2024/EmoGen.

Text-to-video (T2V) synthesis has gained increasing attention in the community in which the recently emerged diffusion models (DMs) have promisingly shown stronger performance than the past approaches. While existing state-of-the-art DMs are competent to achieve high-resolution video generation they may largely suffer from key limitations (e.g. action occurrence disorders crude video motions) with respect to the intricate temporal dynamics modeling one of the crux of video synthesis. In this work we investigate strengthening the awareness of video dynamics for DMs for high-quality T2V generation. Inspired by human intuition we design an innovative dynamic scene manager (dubbed as Dysen) module which includes (step-1) extracting from input text the key actions with proper time-order arrangement (step-2) transforming the action schedules into the dynamic scene graph (DSG) representations and (step-3) enriching the scenes in the DSG with sufficient and reasonable details. Taking advantage of the existing powerful LLMs (e.g. ChatGPT) via in-context learning Dysen realizes (nearly) human-level temporal dynamics understanding. Finally the resulting video DSG with rich action scene details is encoded as fine-grained spatio-temporal features integrated into the backbone T2V DM for video generating. Experiments on popular T2V datasets suggest that our Dysen-VDM consistently outperforms prior arts with significant margins especially in scenarios with complex actions.

Recent advancements in dynamic neural radiance field methods have yielded remarkable outcomes. However these approaches rely on the assumption of sharp input images. When faced with motion blur existing dynamic NeRF methods often struggle to generate high-quality novel views. In this paper we propose DyBluRF a dynamic radiance field approach that synthesizes sharp novel views from a monocular video affected by motion blur. To account for motion blur in input images we simultaneously capture the camera trajectory and object Discrete Cosine Transform (DCT) trajectories within the scene. Additionally we employ a global cross-time rendering approach to ensure consistent temporal coherence across the entire scene. We curate a dataset comprising diverse dynamic scenes that are specifically tailored for our task. Experimental results on our dataset demonstrate that our method outperforms existing approaches in generating sharp novel views from motion-blurred inputs while maintaining spatial-temporal consistency of the scene.

Recent methods such as Score Distillation Sampling (SDS) and Variational Score Distillation (VSD) using 2D diffusion models for text-to-3D generation have demonstrated impressive generation quality. However the long generation time of such algorithms significantly degrades the user experience. To tackle this problem we propose DreamPropeller a drop-in acceleration algorithm that can be wrapped around any existing text-to-3D generation pipeline based on score distillation. Our framework generalizes Picard iterations a classical algorithm for parallel sampling an ODE path and can account for non-ODE paths such as momentum-based gradient updates and changes in dimensions during the optimization process as in many cases of 3D generation. We show that our algorithm trades parallel compute for wallclock time and empirically achieves up to 4.7x speedup with a negligible drop in generation quality for all tested frameworks.

Recent advances in generative AI have unveiled significant potential for the creation of 3D content. However current methods either apply a pre-trained 2D diffusion model with the time-consuming score distillation sampling (SDS) or a direct 3D diffusion model trained on limited 3D data losing generation diversity. In this work we approach the problem by employing a multi-view 2.5D diffusion fine-tuned from a pre-trained 2D diffusion model. The multi-view 2.5D diffusion directly models the structural distribution of 3D data while still maintaining the strong generalization ability of the original 2D diffusion model filling the gap between 2D diffusion-based and direct 3D diffusion-based methods for 3D content generation. During inference multi-view normal maps are generated using the 2.5D diffusion and a novel differentiable rasterization scheme is introduced to fuse the almost consistent multi-view normal maps into a consistent 3D model. We further design a normal-conditioned multi-view image generation module for fast appearance generation given the 3D geometry. Our method is a one-pass diffusion process and does not require any SDS optimization as post-processing. We demonstrate through extensive experiments that our direct 2.5D generation with the specially-designed fusion scheme can achieve diverse mode-seeking-free and high-fidelity 3D content generation in only 10 seconds.

Existing diffusion models for pose-guided human video generation mostly suffer from temporal inconsistency in the generated appearance and poses due to the inherent randomization nature of the generation process. In this paper we propose a novel framework DiffPerformer to synthesize high-fidelity and temporally consistent human video. Without complex architecture modification or costly training DiffPerformer finetunes a pretrained diffusion model on a single video of the target character and introduces an implicit video representation as a proxy to learn temporally consistent guidance for the diffusion model. The guidance is encoded into VAE latent space and an iterative optimization loop is constructed between the implicit video representation and the diffusion model allowing to harness the smooth property of the implicit video representation and the generative capabilities of the diffusion model in a mutually beneficial way. Moreover we propose 3D-aware human flow as a temporal constraint during the optimization to explicitly model the correspondence between driving poses and human appearance. This alleviates the misalignment between guided poses and target performer and therefore maintains the appearance coherence under various motions. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods.

Inverse tone mapping (ITM) aims to reconstruct high dynamic range (HDR) radiance from low dynamic range (LDR) content. Although many deep image ITM methods can generate impressive results the field of video ITM is still to be explored. Processing video sequences by image ITM methods may cause temporal inconsistency. Besides they aren't able to exploit the potentially useful information in the temporal domain. In this paper we analyze the process of video filming and then propose a Global Sample and Local Propagate strategy to better find and utilize temporal clues. To better realize the proposed strategy we design a two-stage pipeline which includes modules named Incremental Clue Aggregation Module and Feature and Clue Propagation Module. They can align and fuse frames effectively under the condition of brightness changes and propagate features and temporal clues to all frames efficiently. Our temporal clues based video ITM method can recover realistic and temporal consistent results with high fidelity in over-exposed regions. Qualitative and quantitative experiments on public datasets show that the proposed method has significant advantages over existing methods.

Recently dataset distillation has paved the way towards efficient machine learning especially for image datasets. However the distillation for videos characterized by an exclusive temporal dimension remains an underexplored domain. In this work we provide the first systematic study of video distillation and introduce a taxonomy to categorize temporal compression. Our investigation reveals that the temporal information is usually not well learned during distillation and the temporal dimension of synthetic data contributes little. The observations motivate our unified framework of disentangling the dynamic and static information in the videos. It first distills the videos into still images as static memory and then compensates the dynamic and motion information with a learnable dynamic memory block. Our method achieves state-of-the-art on video datasets at different scales with notably smaller memory storage budget. Our code is available at https://github.com/yuz1wan/video_distillation.

We present DIRECT-3D a diffusion-based 3D generative model for creating high-quality 3D assets (represented by Neural Radiance Fields) from text prompts. Unlike recent 3D generative models that rely on clean and well-aligned 3D data limiting them to single or few-class generation our model is directly trained on extensive noisy and unaligned `in-the-wild' 3D assets mitigating the key challenge (i.e. data scarcity) in large-scale 3D generation. In particular DIRECT-3D is a tri-plane diffusion model that integrates two innovations: 1) A novel learning framework where noisy data are filtered and aligned automatically during the training process. Specifically after an initial warm-up phase using a small set of clean data an iterative optimization is introduced in the diffusion process to explicitly estimate the 3D pose of objects and select beneficial data based on conditional density. 2) An efficient 3D representation that is achieved by disentangling object geometry and color features with two separate conditional diffusion models that are optimized hierarchically. Given a prompt input our model generates high-quality high-resolution realistic and complex 3D objects with accurate geometric details in seconds. We achieve state-of-the-art performance in both single-class generation and text-to-3D generation. We also demonstrate that DIRECT-3D can serve as a useful 3D geometric prior of objects for example to alleviate the well-known Janus problem in 2D-lifting methods such as DreamFusion.

Customizing pre-trained text-to-image generation model has attracted massive research interest recently due to its huge potential in real-world applications. Although existing methods are able to generate creative content for a novel concept contained in single user-input image their capability are still far from perfection. Specifically most existing methods require fine-tuning the generative model on testing images. Some existing methods do not require fine-tuning while their performance are unsatisfactory. Furthermore the interaction between users and models are still limited to directive and descriptive prompts such as instructions and captions. In this work we build a customization assistant based on pre-trained large language model and diffusion model which can not only perform customized generation in a tuning-free manner but also enable more user-friendly interactions: users can chat with the assistant and input either ambiguous text or clear instruction. Specifically we propose a new framework consists of a new model design and a novel training strategy. The resulting assistant can perform customized generation in 2-5 seconds without any test time fine-tuning. Extensive experiments are conducted competitive results have been obtained across different domains illustrating the effectiveness of the proposed method.

Listening head generation aims to synthesize a non-verbal responsive listener head by modeling the correlation between the speaker and the listener in dynamic conversion. The applications of listener agent generation in virtual interaction have promoted many works achieving diverse and fine-grained motion generation. However they can only manipulate motions through simple emotional labels but cannot freely control the listener's motions. Since listener agents should have human-like attributes (e.g. identity personality) which can be freely customized by users this limits their realism. In this paper we propose a user-friendly framework called CustomListener to realize the free-form text prior guided listener generation. To achieve speaker-listener coordination we design a Static to Dynamic Portrait module (SDP) which interacts with speaker information to transform static text into dynamic portrait token with completion rhythm and amplitude information. To achieve coherence between segments we design a Past Guided Generation module (PGG) to maintain the consistency of customized listener attributes through the motion prior and utilize a diffusion-based structure conditioned on the portrait token and the motion prior to realize the controllable generation. To train and evaluate our model we have constructed two text-annotated listening head datasets based on ViCo and RealTalk which provide text-video paired labels. Extensive experiments have verified the effectiveness of our model.

State-of-the-art personalized text-to-image generation systems are usually trained on a few reference images to learn novel visual representations. However this is likely to incur infringement of copyright for the reference image owners when these images are personal and publicly available. Recent progress has been made in protecting these images from unauthorized use by adding protective noises. Yet current protection methods work under the assumption that these protected images are not changed which is in contradiction to the fact that most public platforms intend to modify user-uploaded content e.g. image compression. This paper introduces a robust watermarking method namely InMark to protect images from unauthorized learning. Inspired by influence functions the proposed method forges protective watermarks on more important pixels for these reference images from both heuristic and statistical perspectives. In this way the personal semantics of these images are under protection even if these images are modified to some extent. Extensive experiments demonstrate that the proposed InMark outperforms previous state-of-the-art methods in both protective performance and robustness.

We introduce Control4D an innovative framework for editing dynamic 4D portraits using text instructions. Our method addresses the prevalent challenges in 4D editing notably the inefficiencies of existing 4D representations and the inconsistent editing effect caused by diffusion-based editors. We first propose GaussianPlanes a novel 4D representation that makes Gaussian Splatting more structured by applying plane-based decomposition in 3D space and time. This enhances both efficiency and robustness in 4D editing. Furthermore we propose to leverage a 4D generator to learn a more continuous generation space from inconsistent edited images produced by the diffusion-based editor which effectively improves the consistency and quality of 4D editing. Comprehensive evaluation demonstrates the superiority of Control4D including significantly reduced training time high-quality rendering and spatial-temporal consistency in 4D portrait editing.

Spatio-temporal video grounding (or STVG) task aims at locating a spatio-temporal tube for a specific instance given a text query. Despite advancements current methods easily suffer the distractors or heavy object appearance variations in videos due to insufficient object information from the text leading to degradation. Addressing this we propose a novel framework context-guided STVG (CG-STVG) which mines discriminative instance context for object in videos and applies it as a supplementary guidance for target localization. The key of CG-STVG lies in two specially designed modules including instance context generation (ICG) which focuses on discovering visual context information (in both appearance and motion) of the instance and instance context refinement (ICR) which aims to improve the instance context from ICG by eliminating irrelevant or even harmful information from the context. During grounding ICG together with ICR are deployed at each decoding stage of a Transformer architecture for instance context learning. Particularly instance context learned from one decoding stage is fed to the next stage and leveraged as a guidance containing rich and discriminative object feature to enhance the target-awareness in decoding feature which conversely benefits generating better new instance context for improving localization finally. Compared to existing methods CG-STVG enjoys object information in text query and guidance from mined instance visual context for more accurate target localization. In our experiments on three benchmarks including HCSTVG-v1/-v2 and VidSTG CG-STVG sets new state-of-the-arts in m_tIoU and m_vIoU on all of them showing efficacy. Code is released at https://github.com/HengLan/CGSTVG.