CVPR 2024 Papers

Diffusion models have shown remarkable results for image generation editing and inpainting. Recent works explore diffusion models for 3D shape generation with neural implicit functions i.e. signed distance function and occupancy function. However they are limited to shapes with closed surfaces which prevents them from generating diverse 3D real-world contents containing open surfaces. In this work we present UDiFF a 3D diffusion model for unsigned distance fields (UDFs) which is capable to generate textured 3D shapes with open surfaces from text conditions or unconditionally. Our key idea is to generate UDFs in spatial-frequency domain with an optimal wavelet transformation which produces a compact representation space for UDF generation. Specifically instead of selecting an appropriate wavelet transformation which requires expensive manual efforts and still leads to large information loss we propose a data-driven approach to learn the optimal wavelet transformation for UDFs. We evaluate UDiFF to show our advantages by numerical and visual comparisons with the latest methods on widely used benchmarks. Page: https://weiqi-zhang.github.io/UDiFF.

Existing learning-based solutions to medical image segmentation have two important shortcomings. First for most new segmentation tasks a new model has to be trained or fine-tuned. This requires extensive resources and machine-learning expertise and is therefore often infeasible for medical researchers and clinicians. Second most existing segmentation methods produce a single deterministic segmentation mask for a given image. In practice however there is often considerable uncertainty about what constitutes the correct segmentation and different expert annotators will often segment the same image differently. We tackle both of these problems with Tyche a framework that uses a context set to generate stochastic predictions for previously unseen tasks without the need to retrain. Tyche differs from other in-context segmentation methods in two important ways. (1) We introduce a novel convolution block architecture that enables interactions among predictions. (2) We introduce in-context test-time augmentation a new mechanism to provide prediction stochasticity. When combined with appropriate model design and loss functions Tyche can predict a set of plausible diverse segmentation candidates for new or unseen medical images and segmentation tasks without the need to retrain. Code available at: https://tyche.csail.mit.edu/.

Visual prompting of large vision language models such as CLIP exhibits intriguing zero-shot capabilities. A manually drawn red circle commonly used for highlighting can guide CLIP's attention to the surrounding region to identify specific objects within an image. Without precise object proposals however it is insufficient for localization. Our novel simple yet effective approach i.e. Differentiable Visual Prompting enables CLIP to zero-shot localize: given an image and a text prompt describing an object we first pick a rendered ellipse from uniformly distributed anchor ellipses on the image grid via visual prompting then use three loss functions to tune the ellipse coefficients to encapsulate the target region gradually. This yields promising experimental results for referring expression comprehension without precisely specified object proposals. In addition we systematically present the limitations of visual prompting inherent in CLIP and discuss potential solutions.

Image denoising is a fundamental task in computer vision. While prevailing deep learning-based supervised and self-supervised methods have excelled in eliminating in-distribution noise their susceptibility to out-of-distribution (OOD) noise remains a significant challenge. The recent emergence of contrastive language-image pre-training (CLIP) model has showcased exceptional capabilities in open-world image recognition and segmentation. Yet the potential for leveraging CLIP to enhance the robustness of low-level tasks remains largely unexplored. This paper uncovers that certain dense features extracted from the frozen ResNet image encoder of CLIP exhibit distortion-invariant and content-related properties which are highly desirable for generalizable denoising. Leveraging these properties we devise an asymmetrical encoder-decoder denoising network which incorporates dense features including the noisy image and its multi-scale features from the frozen ResNet encoder of CLIP into a learnable image decoder to achieve generalizable denoising. The progressive feature augmentation strategy is further proposed to mitigate feature overfitting and improve the robustness of the learnable decoder. Extensive experiments and comparisons conducted across diverse OOD noises including synthetic noise real-world sRGB noise and low-dose CT image noise demonstrate the superior generalization ability of our method.

Open-vocabulary semantic segmentation aims at segmenting arbitrary categories expressed in textual form. Previous works have trained over large amounts of image-caption pairs to enforce pixel-level multimodal alignments. However captions provide global information about the semantics of a given image but lack direct localization of individual concepts. Further training on large-scale datasets inevitably brings significant computational costs. In this paper we propose FreeDA a training-free diffusion-augmented method for open-vocabulary semantic segmentation which leverages the ability of diffusion models to visually localize generated concepts and local-global similarities to match class-agnostic regions with semantic classes. Our approach involves an offline stage in which textual-visual reference embeddings are collected starting from a large set of captions and leveraging visual and semantic contexts. At test time these are queried to support the visual matching process which is carried out by jointly considering class-agnostic regions and global semantic similarities. Extensive analyses demonstrate that FreeDA achieves state-of-the-art performance on five datasets surpassing previous methods by more than 7.0 average points in terms of mIoU and without requiring any training. Our source code is available at https://aimagelab.github.io/freeda/.

A major focus of clinical imaging workflow is disease diagnosis and management leading to medical imaging datasets strongly tied to specific clinical objectives. This scenario has led to the prevailing practice of developing task-specific segmentation models without gaining insights from widespread imaging cohorts. Inspired by the training program of medical radiology residents we propose a shift towards universal medical image segmentation a paradigm aiming to build medical image understanding foundation models by leveraging the diversity and commonality across clinical targets body regions and imaging modalities. Towards this goal we develop Hermes a novel context-prior learning approach to address the challenges of data heterogeneity and annotation differences in medical image segmentation. In a large collection of eleven diverse datasets (2438 3D images) across five modalities (CT PET T1 T2 and cine MRI) and multiple body regions we demonstrate the merit of the universal paradigm over the traditional paradigm on addressing multiple tasks within a single model. By exploiting the synergy across tasks Hermes achieves state-of-the-art performance on all testing datasets and shows superior model scalability. Results on two additional datasets reveals Hermes' strong performance for transfer learning incremental learning and generalization to downstream tasks. Hermes's learned priors demonstrate an appealing trait to reflect the intricate relations among tasks and modalities which aligns with the established anatomical and imaging principles in radiology. The code is available.

Super-resolution (SR) is an ill-posed inverse problem where the size of the set of feasible solutions that are consistent with a given low-resolution image is very large. Many algorithms have been proposed to find a "good" solution among the feasible solutions that strike a balance between fidelity and perceptual quality. Unfortunately all known methods generate artifacts and hallucinations while trying to reconstruct high-frequency (HF) image details. A fundamental question is: Can a model learn to distinguish genuine image details from artifacts? Although some recent works focused on the differentiation of details and artifacts this is a very challenging problem and a satisfactory solution is yet to be found. This paper shows that the characterization of genuine HF details versus artifacts can be better learned by training GAN-based SR models using wavelet-domain loss functions compared to RGB-domain or Fourier-space losses. Although wavelet-domain losses have been used in the literature before they have not been used in the context of the SR task. More specifically we train the discriminator only on the HF wavelet sub-bands instead of on RGB images and the generator is trained by a fidelity loss over wavelet subbands to make it sensitive to the scale and orientation of structures. Extensive experimental results demonstrate that our model achieves better perception-distortion trade-off according to multiple objective measures and visual evaluations.

Diffusion models have demonstrated unprecedented capabilities in image generation. Yet they incorporate and amplify the data bias (e.g. gender age) from the original training set limiting the diversity of generated images. In this paper we propose a diversity-oriented fine-tuning method using reinforcement learning (RL) for diffusion models under the guidance of an image-set-based reward function. Specifically the proposed reward function denoted as Diversity Reward utilizes a set of generated images to evaluate the coverage of the current generative distribution w.r.t. the reference distribution represented by a set of unbiased images. Built on top of the probabilistic method of distribution discrepancy estimation Diversity Reward can measure the relative distribution gap with a small set of images efficiently. We further formulate the diffusion process as a multi-step decision-making problem (MDP) and apply policy gradient methods to fine-tune diffusion models by maximizing the Diversity Reward. The proposed rewards are validated on a post-sampling selection task where a subset of the most diverse images are selected based on Diversity Reward values. We also show the effectiveness of our RL fine-tuning framework on enhancing the diversity of image generation with different types of diffusion models including class-conditional models and text-conditional models e.g. StableDiffusion.

This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars focusing on two key aspects: variability and coordination. Variability allows the avatar to exhibit a wide range of motions even with similar speech content while coordination ensures a harmonious alignment among facial expressions hand gestures and body poses. We aim to achieve both with ProbTalk a unified probabilistic framework designed to jointly model facial hand and body movements in speech. ProbTalk builds on the variational autoencoder (VAE) architecture and incorporates three core designs. First we introduce product quantization (PQ) to the VAE which enriches the representation of complex holistic motion. Second we devise a novel non-autoregressive model that embeds 2D positional encoding into the product-quantized representation thereby preserving essential structure information of the PQ codes. Last we employ a secondary stage to refine the preliminary prediction further sharpening the high-frequency details. Coupling these three designs enables ProbTalk to generate natural and diverse holistic co-speech motions outperforming several state-of-the-art methods in qualitative and quantitative evaluations particularly in terms of realism. Our code and model will be released for research purposes at https://feifeifeiliu.github.io/probtalk/.

Deep Text-to-Image Synthesis (TIS) models such as Stable Diffusion have recently gained significant popularity for creative text-to-image generation. However for domain-specific scenarios tuning-free Text-guided Image Editing (TIE) is of greater importance for application developers. This approach modifies objects or object properties in images by manipulating feature components in attention layers during the generation process. Nevertheless little is known about the semantic meanings that these attention layers have learned and which parts of the attention maps contribute to the success of image editing. In this paper we conduct an in-depth probing analysis and demonstrate that cross-attention maps in Stable Diffusion often contain object attribution information which can result in editing failures. In contrast self-attention maps play a crucial role in preserving the geometric and shape details of the source image during the transformation to the target image. Our analysis offers valuable insights into understanding cross and self-attention mechanisms in diffusion models. Furthermore based on our findings we propose a simplified yet more stable and efficient tuning-free procedure that modifies only the self-attention maps of specified attention layers during the denoising process. Experimental results show that our simplified method consistently surpasses the performance of popular approaches on multiple datasets.

We are witnessing significant breakthroughs in the technology for generating 3D objects from text. Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. Generating entire scenes however remains very challenging as a scene contains multiple 3D objects diverse and scattered. In this work we introduce SceneWiz3D - a novel approach to synthesize high-fidelity 3D scenes from text. We marry the locality of objects with globality of scenes by introducing a hybrid 3D representation - explicit for objects and implicit for scenes. Remarkably an object being represented explicitly can be either generated from text using conventional text-to-3D approaches or provided by users. To configure the layout of the scene and automatically place objects we apply the Particle Swarm Optimization technique during the optimization process. Furthermore it is difficult for certain parts of the scene (e.g. corners occlusion) to receive multi-view supervision leading to inferior geometry. We incorporate an RGBD panorama diffusion model to mitigate it resulting in high-quality geometry. Extensive evaluation supports that our approach achieves superior quality over previous approaches enabling the generation of detailed and view-consistent 3D scenes. Our project website is at https://zqh0253.github.io/SceneWiz3D.\\

Event camera has recently received much attention for low-light image enhancement (LIE) thanks to their distinct advantages such as high dynamic range. However current research is prohibitively restricted by the lack of large-scale real-world and spatial-temporally aligned event-image datasets. To this end we propose a real-world (indoor and outdoor) dataset comprising over 30K pairs of images and events under both low and normal illumination conditions. To achieve this we utilize a robotic arm that traces a consistent non-linear trajectory to curate the dataset with spatial alignment precision under 0.03mm. We then introduce a matching alignment strategy rendering 90% of our dataset with errors less than 0.01s. Based on the dataset we propose a novel event-guided LIE approach called EvLight towards robust performance in real-world low-light scenes. Specifically we first design the multi-scale holistic fusion branch to extract holistic structural and textural information from both events and images. To ensure robustness against variations in the regional illumination and noise we then introduce a Signal-to-Noise-Ratio (SNR)-guided regional feature selection to selectively fuse features of images from regions with high SNR and enhance those with low SNR by extracting regional structural information from events. our EvLight significantly surpasses the frame-based methods e.g. Retinexformer by 1.14 dB and 2.62 dB respectively. Code and datasets are available at https://vlislab22.github.io/eg-lowlight/.

Diffusion models (DMs) excel in photo-realistic image synthesis but their adaptation to LiDAR scene generation poses a substantial hurdle. This is primarily because DMs operating in the point space struggle to preserve the curve-like patterns and 3D geometry of LiDAR scenes which consumes much of their representation power. In this paper we propose LiDAR Diffusion Models (LiDMs) to generate LiDAR-realistic scenes from a latent space tailored to capture the realism of LiDAR scenes by incorporating geometric priors into the learning pipeline. Our method targets three major desiderata: pattern realism geometry realism and object realism. Specifically we introduce curve-wise compression to simulate real-world LiDAR patterns point-wise coordinate supervision to learn scene geometry and patch-wise encoding for a full 3D object context. With these three core designs our method achieves competitive performance on unconditional LiDAR generation in 64-beam scenario and state of the art on conditional LiDAR generation while maintaining high efficiency compared to point-based DMs (up to 107xfaster). Furthermore by compressing LiDAR scenes into a latent space we enable the controllability of DMs with various conditions such as semantic maps camera views and text prompts. Our code and pretrained weights are available at https://github.com/hancyran/LiDAR-Diffusion.

In recent years image manipulation localization has attracted increasing attention due to its pivotal role in ensuring social media security. However effectively identifying forged regions remains an open challenge. The high acquisition cost and the severe scarcity of high-quality data are major factors hindering the performance improvement of modern image manipulation localization systems. To address this issue we propose a novel paradigm termed as CAAA to automatically and accurately annotate the manually forged images from the web at the pixel-level. We further propose a novel metric termed as QES to assist in filtering out unreliable annotations. With CAAA and QES we construct a large-scale diverse and high-quality dataset comprising 123150 manually forged images with mask annotations. Furthermore we develop a new model termed as APSC-Net for accurate image manipulation localization. According to extensive experiments our methods outperforms previous state-of-the-art methods our dataset significantly improves the performance of various models on the widely-used benchmarks. The dataset and codes are publicly available at https://github.com/qcf-568/MIML.

Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature. The users however may face litigation risks owing to the models' tendency to memorize and regurgitate training data during inference. To address this we introduce Anti-Memorization Guidance (AMG) a novel framework employing three targeted guidance strategies for the main causes of memorization: image and caption duplication and highly specific user prompts. Consequently AMG ensures memorization-free outputs while maintaining high image quality and text alignment leveraging the synergy of its guidance methods each indispensable in its own right. AMG also features an innovative automatic detection system for potential memorization during each step of inference process allows selective application of guidance strategies minimally interfering with the original sampling process to preserve output utility. We applied AMG to pretrained Denoising Diffusion Probabilistic Models (DDPM) and Stable Diffusion across various generation tasks. The results demonstrate that AMG is the first approach to successfully eradicates all instances of memorization with no or marginal impacts on image quality and text-alignment as evidenced by FID and CLIP scores.

We develop a novel vectorized image representation scheme accommodating both shape/geometry and texture in a decoupled way particularly tailored for reconstruction and editing tasks of artistic/design images such as Emojis and Cliparts. In the heart of this representation is a set of sparsely and unevenly located 2D control points. On one hand these points constitute a collection of parametric/vectorized geometric primitives (e.g. curves and closed shapes) describing the shape characteristics of the target image. On the other hand local texture codes in terms of implicit neural network parameters are spatially distributed into each control point yielding local coordinate-to-RGB mappings within the anchored region of each control point. In the meantime a zero-shot learning algorithm is developed to decompose an arbitrary raster image into the above representation for the sake of high-fidelity image vectorization with convenient editing ability. Extensive experiments on a series of image vectorization and editing tasks well demonstrate the high accuracy offered by our proposed method with a significantly higher image compression ratio over prior art.

Vanilla text-to-image diffusion models struggle with generating accurate human images commonly resulting in imperfect anatomies such as unnatural postures or disproportionate limbs. Existing methods address this issue mostly by fine-tuning the model with extra images or adding additional controls --- human-centric priors such as pose or depth maps --- during the image generation phase. This paper explores the integration of these human-centric priors directly into the model fine-tuning stage essentially eliminating the need for extra conditions at the inference stage. We realize this idea by proposing a human-centric alignment loss to strengthen human-related information from the textual prompts within the cross-attention maps. To ensure semantic detail richness and human structural accuracy during fine-tuning we introduce scale-aware and step-wise constraints within the diffusion process according to an in-depth analysis of the cross-attention layer. Extensive experiments show that our method largely improves over state-of-the-art text-to-image models to synthesize high-quality human images based on user-written prompts.

This paper explores the possibility of extending the capability of pre-trained neural image compressors (e.g. adapting to new data or target bitrates) without breaking backward compatibility the ability to decode bitstreams encoded by the original model. We refer to this problem as continual learning of image compression. Our initial findings show that baseline solutions such as end-to-end fine-tuning do not preserve the desired backward compatibility. To tackle this we propose a knowledge replay training strategy that effectively addresses this issue. We also design a new model architecture that enables more effective continual learning than existing baselines. Experiments are conducted for two scenarios: data-incremental learning and rate-incremental learning. The main conclusion of this paper is that neural image compressors can be fine-tuned to achieve better performance (compared to their pre-trained version) on new data and rates without compromising backward compatibility. The code is publicly available online.