CVPR 2024 Papers

In real-world scenarios image recognition tasks such as semantic segmentation and object detection often pose greater challenges due to the lack of information available within low-resolution (LR) content. Image super-resolution (SR) is one of the promising solutions for addressing the challenges. However due to the ill-posed property of SR it is challenging for typical SR methods to restore task-relevant high-frequency contents which may dilute the advantage of utilizing the SR method. Therefore in this paper we propose Super-Resolution for Image Recognition (SR4IR) that effectively guides the generation of SR images beneficial to achieving satisfactory image recognition performance when processing LR images. The critical component of our SR4IR is the task-driven perceptual (TDP) loss that enables the SR network to acquire task-specific knowledge from a network tailored for a specific task. Moreover we propose a cross-quality patch mix and an alternate training framework that significantly enhances the efficacy of the TDP loss by addressing potential problems when employing the TDP loss. Through extensive experiments we demonstrate that our SR4IR achieves outstanding task performance by generating SR images useful for a specific image recognition task including semantic segmentation object detection and image classification. The implementation code is available at https://github.com/JaehaKim97/SR4IR.

Sampling from the posterior distribution in latent diffusion models for inverse problems is computationally challenging. Existing methods often rely on Tweedie's first-order moments that tend to induce biased results. Second-order approximations are computationally prohibitive making standard reverse diffusion processes intractable for posterior sampling. This paper presents Second-order Tweedie sampler from Surrogate Loss (STSL) a novel sampler offering efficiency comparable to first-order Tweedie while enabling tractable reverse processes using second-order approximation. Theoretical results reveal that our approach utilizing for the trace of the Hessian with only O(1) compute establishes a lower bound through a surrogate loss and enables a tractable reverse process. We show STSL outperforms SoTA solvers PSLD and P2L by reducing neural function evaluations by 4X and 8X respectively while enhancing sampling quality on FFHQ ImageNet and COCO benchmarks. Moreover STSL extends to text guided image editing and mitigates residual distortions in corrupted images. To our best knowledge this is the first work to offer an efficient second order approximation for solving inverse problems using latent diffusion and editing real world images with corruptions.

Generating large-scale 3D scenes cannot simply apply existing 3D object synthesis technique since 3D scenes usually hold complex spatial configurations and consist of a number of objects at varying scales. We thus propose a practical and efficient 3D representation that incorporates an equivariant radiance field with the guidance of a bird's-eye view (BEV) map. Concretely objects of synthesized 3D scenes could be easily manipulated through steering the corresponding BEV maps. Moreover by adequately incorporating positional encoding and low-pass filters into the generator the representation becomes equivariant to the given BEV map. Such equivariance allows us to produce large-scale even infinite-scale 3D scenes via synthesizing local scenes and then stitching them with smooth consistency. Extensive experiments on 3D scene datasets demonstrate the effectiveness of our approach. Our project website is at: https://https://zqh0253.github.io/BerfScene.

Representing signals using coordinate networks dominates the area of inverse problems recently and is widely applied in various scientific computing tasks. Still there exists an issue of spectral bias in coordinate networks limiting the capacity to learn high-frequency components. This problem is caused by the pathological distribution of the neural tangent kernel's (NTK's) eigenvalues of coordinate networks. We find that this pathological distribution could be improved using the classical batch normalization (BN) which is a common deep learning technique but rarely used in coordinate networks. BN greatly reduces the maximum and variance of NTK's eigenvalues while slightly modifies the mean value considering the max eigenvalue is much larger than the most this variance change results in a shift of eigenvalues' distribution from a lower one to a higher one therefore the spectral bias could be alleviated (see Fig. 1). This observation is substantiated by the significant improvements of applying BN-based coordinate networks to various tasks including the image compression computed tomography reconstruction shape representation magnetic resonance imaging and novel view synthesis.

Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However DMs reflect the biases present in the training datasets. This is especially concerning in the context of faces where the DM prefers one demographic subgroup vs others (eg. female vs male). In this work we present a method for debiasing DMs without relying on additional reference data or model retraining. Specifically we propose Distribution Guidance which enforces the generated images to follow the prescribed attribute distribution. To realize this we build on the key insight that the latent features of denoising UNet hold rich demographic semantics and the same can be leveraged to guide debiased generation. We train Attribute Distribution Predictor (ADP) - a small mlp that maps the latent features to the distribution of attributes. ADP is trained with pseudo labels generated from existing attribute classifiers. The proposed Distribution Guidance with ADP enables us to do fair generation. Our method reduces bias across single/multiple attributes and outperforms the baseline by a significant margin for unconditional and text-conditional diffusion models. Further we present a downstream task of training a fair attribute classifier by augmenting the training set with our generated data.

The recently emerging text-to-motion advances have spired numerous attempts for convenient and interactive human motion generation. Yet existing methods are largely limited to generating body motions only without considering the rich two-hand motions let alone handling various conditions like body dynamics or texts. To break the data bottleneck we propose BOTH57M a novel multi-modal dataset for two-hand motion generation. Our dataset includes accurate motion tracking for the human body and hands and provides pair-wised finger-level hand annotations and body descriptions. We further provide a strong baseline method BOTH2Hands for the novel task: generating vivid two-hand motions from both implicit body dynamics and explicit text prompts. We first warm up two parallel body-to-hand and text-to-hand diffusion models and then utilize the cross-attention transformer for motion blending. Extensive experiments and cross-validations demonstrate the effectiveness of our approach and dataset for generating convincing two-hand motions from the hybrid body-and-textual conditions. Our dataset and code will be disseminated to the community for future research which can be found at https://github.com/Godheritage/BOTH2Hands.

Diffusion models have made tremendous progress in text-driven image and video generation. Now text-to-image foundation models are widely applied to various downstream image synthesis tasks such as controllable image generation and image editing while downstream video synthesis tasks are less explored for several reasons. First it requires huge memory and computation overhead to train a video generation foundation model. Even with video foundation models additional costly training is still required for downstream video synthesis tasks. Second although some works extend image diffusion models into videos in a training-free manner temporal consistency cannot be well preserved. Finally these adaption methods are specifically designed for one task and fail to generalize to different tasks. To mitigate these issues we propose a training-free general-purpose video synthesis framework coined as BIVDiff via bridging specific image diffusion models and general text-to-video foundation diffusion models. Specifically we first use a specific image diffusion model (e.g. ControlNet and Instruct Pix2Pix) for frame-wise video generation then perform Mixed Inversion on the generated video and finally input the inverted latents into the video diffusion models (e.g. VidRD and ZeroScope) for temporal smoothing. This decoupled framework enables flexible image model selection for different purposes with strong task generalization and high efficiency. To validate the effectiveness and general use of BIVDiff we perform a wide range of video synthesis tasks including controllable video generation video editing video inpainting and outpainting.

Large Language Models(LLMs) have shown remarkable emergent abilities in unifying almost all (if not every) NLP tasks. In the human motion-related realm however researchers still develop siloed models for each task. Inspired by InstuctGPT[??] and the generalist concept behind Gato [??] we introduce AvatarGPT an All-in-One framework for motion understanding planning generations as well as other tasks such as motion in-between synthesis. AvatarGPT treats each task as one type of instruction fine-tuned on the shared LLM. All the tasks are seamlessly interconnected with language as the universal interface constituting a closed-loop within the framework. To achieve this human motion sequences are first encoded as discrete tokens which serve as the extended vocabulary of LLM. Then an unsupervised pipeline to generate natural language descriptions of human action sequences from in-the-wild videos is developed. Finally all tasks are jointly trained. Extensive experiments show that AvatarGPT achieves SOTA on low-level tasks and promising results on high-level tasks demonstrating the effectiveness of our proposed All-in-One framework. Moreover for the first time AvatarGPT enables a principled approach by iterative traversal of the tasks within the closed-loop for unlimited long-motion synthesis.

We propose a framework for automatic colorization that allows for iterative editing and modifications. The core of our framework lies in an imagination module: by understanding the content within a grayscale image we utilize a pre-trained image generation model to generate multiple images that contain the same content. These images serve as references for coloring mimicking the process of human experts. As the synthesized images can be imperfect or different from the original grayscale image we propose a Reference Refinement Module to select the optimal reference composition. Unlike most previous end-to-end automatic colorization algorithms our framework allows for iterative and localized modifications of the colorization results because we explicitly model the coloring samples. Extensive experiments demonstrate the superiority of our framework over existing automatic colorization algorithms in editability and flexibility. Project page: https://xy-cong.github.io/imagine-colorization/.

Editable 3D-aware generation which supports user-interacted editing has witnessed rapid development recently. However existing editable 3D GANs either fail to achieve high-accuracy local editing or suffer from huge computational costs. We propose AttriHuman-3D an editable 3D human generation model which address the aforementioned problems with attribute decomposition and indexing. The core idea of the proposed model is to generate all attributes (e.g. human body hair clothes and so on) in an overall attribute space with six feature planes which are then decomposed and manipulated with different attribute indexes. To precisely extract features of different attributes from the generated feature planes we propose a novel attribute indexing method as well as an orthogonal projection regularization to enhance the disentanglement. We also introduce a hyper-latent training strategy and an attribute-specific sampling strategy to avoid style entanglement and misleading punishment from the discriminator. Our method allows users to interactively edit selected attributes in the generated 3D human avatars while keeping others fixed. Both qualitative and quantitative experiments demonstrate that our model provides a strong disentanglement between different attributes allows fine-grained image editing and generates high-quality 3D human avatars.

Diffusion models (DMs) have exhibited superior performance in generating high-quality and diverse images. However this exceptional performance comes at the cost of expensive generation process particularly due to the heavily used attention module in leading models. Existing works mainly adopt a retraining process to enhance DM efficiency. This is computationally expensive and not very scalable. To this end we introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM) framework that leverages attention maps to perform run-time pruning of redundant tokens without the need for any retraining. Specifically for single-denoising-step pruning we develop a novel ranking algorithm Generalized Weighted Page Rank (G-WPR) to identify redundant tokens and a similarity-based recovery method to restore tokens for the convolution operation. In addition we propose a Denoising-Steps-Aware Pruning (DSAP) approach to adjust the pruning budget across different denoising timesteps for better generation quality. Extensive evaluations show that AT-EDM performs favorably against prior art in terms of efficiency (e.g. 38.8% FLOPs saving and up to 1.53x speed-up over Stable Diffusion XL) while maintaining nearly the same FID and CLIP scores as the full model.

Recent thrilling progress in large-scale text-to-image (T2I) models has unlocked unprecedented synthesis quality of AI-generated content (AIGC) including image generation 3D and video composition. Further personalized techniques enable appealing customized production of a novel concept given only several images as reference. However an intriguing problem persists: Is it possible to capture multiple novel concepts from one single reference image? In this paper we identify that existing approaches fail to preserve visual consistency with the reference image and eliminate cross-influence from concepts. To alleviate this we propose an attention calibration mechanism to improve the concept-level understanding of the T2I model. Specifically we first introduce new learnable modifiers bound with classes to capture attributes of multiple concepts. Then the classes are separated and strengthened following the activation of the cross-attention operation ensuring comprehensive and self-contained concepts. Additionally we suppress the attention activation of different classes to mitigate mutual influence among concepts. Together our proposed method dubbed DisenDiff can learn disentangled multiple concepts from one single image and produce novel customized images with learned concepts. We demonstrate that our method outperforms the current state of the art in both qualitative and quantitative evaluations. More importantly our proposed techniques are compatible with LoRA and inpainting pipelines enabling more interactive experiences.

Monocular depth estimation has experienced significant progress on terrestrial images in recent years thanks to deep learning advancements. But it remains inadequate for underwater scenes primarily due to data scarcity. Given the inherent challenges of light attenuation and backscatter in water acquiring clear underwater images or precise depth is notably difficult and costly. To mitigate this issue learning-based approaches often rely on synthetic data or turn to self- or unsupervised manners. Nonetheless their performance is often hindered by domain gap and looser constraints. In this paper we propose a novel pipeline for generating photorealistic underwater images using accurate terrestrial depth. This approach facilitates the supervised training of models for underwater depth estimation effectively reducing the performance disparity between terrestrial and underwater environments. Contrary to previous synthetic datasets that merely apply style transfer to terrestrial images without scene content change our approach uniquely creates vivid non-existent underwater scenes by leveraging terrestrial depth data through the innovative Stable Diffusion model. Specifically we introduce a specialized Depth2Underwater ControlNet trained on prepared \ Underwater Depth Text\ data triplets for this generation task. Our newly developed dataset Atlantis enables terrestrial depth estimation models to achieve considerable improvements on unseen underwater scenes surpassing their terrestrial pretrained counterparts both quantitatively and qualitatively. Moreover we further show its practical utility by applying the improved depth in underwater image enhancement and its smaller domain gap from the LLVM perspective. Code and dataset are publicly available at https://github.com/zkawfanx/Atlantis.

This work introduces ArtAdapter a transformative text-to-image (T2I) style transfer framework that transcends traditional limitations of color brushstrokes and object shape capturing high-level style elements such as composition and distinctive artistic expression. The integration of a multi-level style encoder with our proposed explicit adaptation mechanism enables ArtAdapter to achieve unprecedented fidelity in style transfer ensuring close alignment with textual descriptions. Additionally the incorporation of an Auxiliary Content Adapter (ACA) effectively separates content from style alleviating the borrowing of content from style references. Moreover our novel fast finetuning approach could further enhance zero-shot style representation while mitigating the risk of overfitting. Comprehensive evaluations confirm that ArtAdapter surpasses current state-of-the-art methods.

Super-resolution (SR) and image generation are important tasks in computer vision and are widely adopted in real-world applications. Most existing methods however generate images only at fixed-scale magnification and suffer from over-smoothing and artifacts. Additionally they do not offer enough diversity of output images nor image consistency at different scales. Most relevant work applied Implicit Neural Representation (INR) to the denoising diffusion model to obtain continuous-resolution yet diverse and high-quality SR results. Since this model operates in the image space the larger the resolution of image is produced the more memory and inference time is required and it also does not maintain scale-specific consistency. We propose a novel pipeline that can super-resolve an input image or generate from a random noise a novel image at arbitrary scales. The method consists of a pretrained auto-encoder a latent diffusion model and an implicit neural decoder and their learning strategies. The proposed method adopts diffusion processes in a latent space thus efficient yet aligned with output image space decoded by MLPs at arbitrary scales. More specifically our arbitrary-scale decoder is designed by the symmetric decoder w/o up-scaling from the pretrained auto-encoder and Local Implicit Image Function (LIIF) in series. The latent diffusion process is learnt by the denoising and the alignment losses jointly. Errors in output images are backpropagated via the fixed decoder improving the quality of output images. In the extensive experiments using multiple public benchmarks on the two tasks i.e. image super-resolution and novel image generation at arbitrary scales the proposed method outperforms relevant methods in metrics of image quality diversity and scale consistency. It is significantly better than the relevant prior-art in the inference speed and memory usage.

Recent advancements in text-to-image technology have significantly advanced the field of image customization. Among various applications the task of customizing diverse scenes for user-specified composited elements holds great application value but has not been extensively explored. Addressing this gap we propose AnyScene a specialized framework designed to create varied scenes from composited foreground using textual prompts. AnyScene addresses the primary challenges inherent in existing methods particularly scene disharmony due to a lack of foreground semantic understanding and distortion of foreground elements. Specifically we develop a foreground injection module that guides a pre-trained diffusion model to generate cohesive scenes in visual harmony with the provided foreground. To enhance robust generation we implement a layout control strategy that prevents distortions of foreground elements. Furthermore an efficient image blending mechanism seamlessly reintegrates foreground details into the generated scenes producing outputs with overall visual harmony and precise foreground details. In addition we propose a new benchmark and a series of quantitative metrics to evaluate this proposed image customization task. Extensive experimental results demonstrate the effectiveness of AnyScene which confirms its potential in various applications.

We present the pioneering Large Visual Motion Model (LVMM) meticulously engineered to analyze the intrinsic dynamics encapsulated within real-world imagery. Our model fortified with a wealth of prior knowledge extracted from billions of image pairs demonstrates promising results in predicting a diverse spectrum of scene dynamics. As a result it can infuse any generic image with authentic dynamic effects enhancing its visual allure.

Character Animation aims to generating character videos from still images through driving signals. Currently diffusion models have become the mainstream in visual generation research owing to their robust generative capabilities. However challenges persist in the realm of image-to-video especially in character animation where temporally maintaining consistency with detailed information from character remains a formidable problem. In this paper we leverage the power of diffusion models and propose a novel framework tailored for character animation. To preserve consistency of intricate appearance features from reference image we design ReferenceNet to merge detail features via spatial attention. To ensure controllability and continuity we introduce an efficient pose guider to direct character's movements and employ an effective temporal modeling approach to ensure smooth inter-frame transitions between video frames. By expanding the training data our approach can animate arbitrary characters yielding superior results in character animation compared to other image-to-video methods. Furthermore we evaluate our method on image animation benchmarks achieving state-of-the-art results.