CVPR 2024 Papers

Diffusion-based text-to-image generative models e.g. Stable Diffusion have revolutionized the field of content generation enabling significant advancements in areas like image editing and video synthesis. Despite their formidable capabilities these models are not without their limitations. It is still challenging to synthesize an image that aligns well with the input text and multiple runs with carefully crafted prompts are required to achieve satisfactory results. To mitigate these limitations numerous studies have endeavored to fine-tune the pre-trained diffusion models i.e.. UNet utilizing various technologies. Yet amidst these efforts a pivotal question of text-to-image diffusion model training has remained largely unexplored: Is it possible and feasible to fine-tune the text encoder to improve the performance of text-to-image diffusion models? Our findings reveal that instead of replacing the CLIP text encoder used in Stable Diffusion with other large language models we can enhance it through our proposed fine-tuning approach TextCraftor leading to substantial improvements in quantitative benchmarks and human assessments. Interestingly our technique also empowers controllable image generation through the interpolation of different text encoders fine-tuned with various rewards. We also demonstrate that TextCraftor is orthogonal to UNet finetuning and can be combined to further improve generative quality.

In the digital era QR codes serve as a linchpin connecting virtual and physical realms. Their pervasive integration across various applications highlights the demand for aesthetically pleasing codes without compromised scannability. However prevailing methods grapple with the intrinsic challenge of balancing customization and scannability. Notably stable-diffusion models have ushered in an epoch of high-quality customizable content generation. This paper introduces Text2QR a pioneering approach leveraging these advancements to address a fundamental challenge: concurrently achieving user-defined aesthetics and scanning robustness. To ensure stable generation of aesthetic QR codes we introduce the QR Aesthetic Blueprint (QAB) module generating a blueprint image exerting control over the entire generation process. Subsequently the Scannability Enhancing Latent Refinement (SELR) process refines the output iteratively in the latent space enhancing scanning robustness. This approach harnesses the potent generation capabilities of stable-diffusion models navigating the trade-off between image aesthetics and QR code scannability. Our experiments demonstrate the seamless fusion of visual appeal with the practical utility of aesthetic QR codes markedly outperforming prior methods. Codes are available at https://github.com/mulns/Text2QR

This paper introduces the first text-guided work for generating the sequence of hand-object interaction in 3D. The main challenge arises from the lack of labeled data where existing ground-truth datasets are nowhere near generalizable in interaction type and object category which inhibits the modeling of diverse 3D hand-object interaction with the correct physical implication (e.g. contacts and semantics) from text prompts. To address this challenge we propose to decompose the interaction generation task into two subtasks: hand-object contact generation; and hand-object motion generation. For contact generation a VAE-based network takes as input a text and an object mesh and generates the probability of contacts between the surfaces of hands and the object during the interaction. The network learns a variety of local geometry structure of diverse objects that is independent of the objects' category and thus it is applicable to general objects. For motion generation a Transformer-based diffusion model utilizes this 3D contact map as a strong prior for generating physically plausible hand-object motion as a function of text prompts by learning from the augmented labeled dataset; where we annotate text labels from many existing 3D hand and object motion data. Finally we further introduce a hand refiner module that minimizes the distance between the object surface and hand joints to improve the temporal stability of the object-hand contacts and to suppress the penetration artifacts. In the experiments we demonstrate that our method can generate more realistic and diverse interactions compared to other baseline methods. We also show that our method is applicable to unseen objects. We will release our model and newly labeled data as a strong foundation for future research. Codes and data are available in: https://github.com/JunukCha/Text2HOI.

This paper for the first time explores text-to-image diffusion models for Zero-Shot Sketch-based Image Retrieval (ZS-SBIR). We highlight a pivotal discovery: the capacity of text-to-image diffusion models to seamlessly bridge the gap between sketches and photos. This proficiency is underpinned by their robust cross-modal capabilities and shape bias findings that are substantiated through our pilot studies. In order to harness pre-trained diffusion models effectively we introduce a straightforward yet powerful strategy focused on two key aspects: selecting optimal feature layers and utilising visual and textual prompts. For the former we identify which layers are most enriched with information and are best suited for the specific retrieval requirements (category-level or fine-grained). Then we employ visual and textual prompts to guide the model's feature extraction process enabling it to generate more discriminative and contextually relevant cross-modal representations. Extensive experiments on several benchmark datasets validate significant performance improvements.

Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors these methods often lead to geometric anomalies and multi-view inconsistency. Recently researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches we propose Bidirectional Diffusion (BiDiff) a unified framework that incorporates both a 3D and a 2D diffusion process to preserve both 3D fidelity and 2D texture richness respectively. Moreover as a simple combination may yield inconsistent generation results we further bridge them with novel bidirectional guidance. In addition our method can be used as an initialization of optimization-based models to further improve the quality of 3D model and efficiency of optimization reducing the process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality diverse and scalable 3D generation. Project website https://bidiff.github.io/.

In this paper we introduce the problem of zero-shot text-guided exploration of the solutions to open-domain image super-resolution. Our goal is to allow users to explore diverse semantically accurate reconstructions that preserve data consistency with the low-resolution inputs for different large downsampling factors without explicitly training for these specific degradations. We propose two approaches for zero-shot text-guided super-resolution - i) modifying the generative process of text-to-image (T2I) diffusion models to promote consistency with low-resolution inputs and ii) incorporating language guidance into zero-shot diffusion-based restoration methods. We show that the proposed approaches result in diverse solutions that match the semantic meaning provided by the text prompt while preserving data consistency with the degraded inputs. We evaluate the proposed baselines for the task of extreme super-resolution and demonstrate advantages in terms of restoration quality diversity and explorability of solutions.

Diffusion models are generative models with impressive text-to-image synthesis capabilities and have spurred a new wave of creative methods for classical machine learning tasks. However the best way to harness the perceptual knowledge of these generative models for visual tasks is still an open question. Specifically it is unclear how to use the prompting interface when applying diffusion backbones to vision tasks. We find that automatically generated captions can improve text-image alignment and significantly enhance a model's cross-attention maps leading to better perceptual performance. Our approach improves upon the current state-of-the-art in diffusion-based semantic segmentation on ADE20K and the current overall SOTA for depth estimation on NYUv2. Furthermore our method generalizes to the cross-domain setting. We use model personalization and caption modifications to align our model to the target domain and find improvements over unaligned baselines. Our cross-domain object detection model trained on Pascal VOC achieves SOTA results on Watercolor2K. Our cross-domain segmentation method trained on Cityscapes achieves SOTA results on Dark Zurich-val and Nighttime Driving. Project page: vision.caltech.edu/TADP/. Code: github.com/damaggu/TADP

Text-guided 3D face synthesis has achieved remarkable results by leveraging text-to-image (T2I) diffusion models. However most existing works focus solely on the direct generation ignoring the editing restricting them from synthesizing customized 3D faces through iterative adjustments. In this paper we propose a unified text-guided framework from face generation to editing. In the generation stage we propose a geometry-texture decoupled generation to mitigate the loss of geometric details caused by coupling. Besides decoupling enables us to utilize the generated geometry as a condition for texture generation yielding highly geometry-texture aligned results. We further employ a fine-tuned texture diffusion model to enhance texture quality in both RGB and YUV space. In the editing stage we first employ a pre-trained diffusion model to update facial geometry or texture based on the texts. To enable sequential editing we introduce a UV domain consistency preservation regularization preventing unintentional changes to irrelevant facial attributes. Besides we propose a self-guided consistency weight strategy to improve editing efficacy while preserving consistency. Through comprehensive experiments we showcase our method's superiority in face synthesis.

We present HAAR a new strand-based generative model for 3D human hairstyles. Specifically based on textual inputs HAAR produces 3D hairstyles that could be used as production-level assets in modern computer graphics engines. Current AI-based generative models take advantage of powerful 2D priors to reconstruct 3D content in the form of point clouds meshes or volumetric functions. However by using the 2D priors they are intrinsically limited to only recovering the visual parts. Highly occluded hair structures can not be reconstructed with those methods and they only model the "outer shell" which is not ready to be used in physics-based rendering or simulation pipelines. In contrast we propose a first text-guided generative method that uses 3D hair strands as an underlying representation. Leveraging 2D visual question-answering (VQA) systems we automatically annotate synthetic hair models that are generated from a small set of artist-created hairstyles. This allows us to train a latent diffusion model that operates in a common hairstyle UV space. In qualitative and quantitative studies we demonstrate the capabilities of the proposed model and compare it to existing hairstyle generation approaches. For results please refer to our project page https://haar.is.tue.mpg.de/.

This paper focuses on synthesizing high-quality and complete textures directly on the surface of 3D models within 3D space. 2D diffusion-based methods face challenges in generating 2D texture maps due to the infinite possibilities of UV mapping for a given 3D mesh. Utilizing point clouds helps circumvent variations arising from diverse mesh topologies and UV mappings. Nevertheless achieving dense point clouds to accurately represent texture details poses a challenge due to limited computational resources. To address these challenges we propose an efficient octree-based diffusion pipeline called TexOct. Our method starts by sampling a point cloud from the surface of a given 3D model with each point containing texture noise values. We utilize an octree structure to efficiently represent this point cloud. Additionally we introduce an innovative octree-based diffusion model that leverages the denoising capabilities of the Denoising Diffusion Probabilistic Model (DDPM). This model gradually reduces the texture noise on the octree nodes resulting in the restoration of fine texture. Experimental results on ShapeNet demonstrate that TexOct effectively generates high-quality 3D textures in both unconditional and text / image-conditional scenarios.

Reconstructing human-object interaction in 3D from a single RGB image is a challenging task and existing data driven methods do not generalize beyond the objects present in the carefully curated 3D interaction datasets. Capturing large-scale real data to learn strong interaction and 3D shape priors is very expensive due to the combinatorial nature of human-object interactions. In this paper we propose ProciGen (Procedural interaction Generation) a method to procedurally generate datasets with both plausible interaction and diverse object variation. We generate 1M+ human-object interaction pairs in 3D and leverage this large-scale data to train our HDM (Hierarchical Diffusion Model) a novel method to reconstruct interacting human and unseen object instances without any templates. Our HDM is an image-conditioned diffusion model that learns both realistic interaction and highly accurate human and object shapes. Experiments show that our HDM trained with ProciGen significantly outperforms prior methods that require template meshes and our dataset allows training methods with strong generalization ability to unseen object instances. Our code and data are released.

Generative models e.g. Stable Diffusion have enabled the creation of photorealistic images from text prompts. Yet the generation of 360-degree panorama images from text remains a challenge particularly due to the dearth of paired text-panorama data and the domain gap between panorama and perspective images. In this paper we introduce a novel dual-branch diffusion model named PanFusion to generate a 360-degree image from a text prompt. We leverage the stable diffusion model as one branch to provide prior knowledge in natural image generation and register it to another panorama branch for holistic image generation. We propose a unique cross-attention mechanism with projection awareness to minimize distortion during the collaborative denoising process. Our experiments validate that PanFusion surpasses existing methods and thanks to its dual-branch structure can integrate additional constraints like room layout for customized panorama outputs.

We present a scene representation that brings vision and touch into a shared 3D space which we call a tactile-augmented radiance field. This representation capitalizes on two key insights: (i) ubiquitous vision-based touch sensors are built on perspective cameras and (ii) visually and structurally similar regions of a scene share the same tactile features. We use these insights to train a conditional diffusion model that provided with an RGB image and a depth map rendered from a neural radiance field generates its corresponding tactile "image". To train this diffusion model we collect the largest collection of spatially-aligned visual and tactile data. Through qualitative and quantitative experiments we demonstrate the accuracy of our cross-modal generative model and the utility of collected and rendered visual-tactile pairs across a range of downstream tasks. Project page: https://dou-yiming.github.io/TaRF

Most diffusion models assume that the reverse process adheres to a Gaussian distribution. However this approximation has not been rigorously validated especially at singularities where t=0 and t=1. Improperly dealing with such singularities leads to an average brightness issue in applications and limits the generation of images with extreme brightness or darkness. We primarily focus on tackling singularities from both theoretical and practical perspectives. Initially we establish the error bounds for the reverse process approximation and showcase its Gaussian characteristics at singularity time steps. Based on this theoretical insight we confirm the singularity at t=1 is conditionally removable while it at t=0 is an inherent property. Upon these significant conclusions we propose a novel plug-and-play method SingDiffusion to address the initial singular time step sampling which not only effectively resolves the average brightness issue for a wide range of diffusion models without extra training efforts but also enhances their generation capability in achieving notable lower FID scores.

Recent advances in text-to-video generation have demonstrated the utility of powerful diffusion models. Nevertheless the problem is not trivial when shaping diffusion models to animate static image (i.e. image-to-video generation). The difficulty originates from the aspect that the diffusion process of subsequent animated frames should not only preserve the faithful alignment with the given image but also pursue temporal coherence among adjacent frames. To alleviate this we present TRIP a new recipe of image-to-video diffusion paradigm that pivots on image noise prior derived from static image to jointly trigger inter-frame relational reasoning and ease the coherent temporal modeling via temporal residual learning. Technically the image noise prior is first attained through one-step backward diffusion process based on both static image and noised video latent codes. Next TRIP executes a residual-like dual-path scheme for noise prediction: 1) a shortcut path that directly takes image noise prior as the reference noise of each frame to amplify the alignment between the first frame and subsequent frames; 2) a residual path that employs 3D-UNet over noised video and static image latent codes to enable inter-frame relational reasoning thereby easing the learning of the residual noise for each frame. Furthermore both reference and residual noise of each frame are dynamically merged via attention mechanism for final video generation. Extensive experiments on WebVid-10M DTDB and MSR-VTT datasets demonstrate the effectiveness of our TRIP for image-to-video generation. Please see our project page at https://trip-i2v.github.io/TRIP/.

Recently diffusion models have emerged as a new powerful generative method for 3D point cloud generation tasks. However few works study the effect of the architecture of the diffusion model in the 3D point cloud resorting to the typical UNet model developed for 2D images. Inspired by the wide adoption of Transformers we study the complementary role of convolution (from UNet) and attention (from Transformers). We discover that their respective importance change according to the timestep in the diffusion process. At early stage attention has an outsized influence because Transformers are found to generate the overall shape more quickly and at later stages when adding fine detail convolution starts having a larger impact on the generated point cloud's local surface quality. In light of this observation we propose a time-varying two-stream denoising model combined with convolution layers and transformer blocks. We generate an optimizable mask from each timestep to reweigh global and local features obtaining time-varying fused features. Experimentally we demonstrate that our proposed method quantitatively outperforms other state-of-the-art methods regarding visual quality and diversity. Code is avaiable github.com/Zhiyuan-R/Tiger-Time-varying-Diffusion-Model-for-Point-Cloud-Generation.

Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g. a woman's photo) and a text description (e.g. "a woman is drinking water."). Existing TI2V frameworks often require costly training on video-text datasets and specific model designs for text and image conditioning. In this paper we propose TI2V-Zero a zero-shot tuning-free method that empowers a pretrained text-to-video (T2V) diffusion model to be conditioned on a provided image enabling TI2V generation without any optimization fine-tuning or introducing external modules. Our approach leverages a pretrained T2V diffusion foundation model as the generative prior. To guide video generation with the additional image input we propose a "repeat-and-slide" strategy that modulates the reverse denoising process allowing the frozen diffusion model to synthesize a video frame-by-frame starting from the provided image. To ensure temporal continuity we employ a DDPM inversion strategy to initialize Gaussian noise for each newly synthesized frame and a resampling technique to help preserve visual details. We conduct comprehensive experiments on both domain-specific and open-domain datasets where TI2V-Zero consistently outperforms a recent open-domain TI2V model. Furthermore we show that TI2V-Zero can seamlessly extend to other tasks such as video infilling and prediction when provided with more images. Its autoregressive design also supports long video generation.

The Diffusion model a prevalent framework for image generation encounters significant challenges in terms of broad applicability due to its extended inference times and substantial memory requirements. Efficient Post-training Quantization (PTQ) is pivotal for addressing these issues in traditional models. Different from traditional models diffusion models heavily depend on the time-step t to achieve satisfactory multi-round denoising. Usually t from the finite set \ 1 \ldots T\ is encoded to a temporal feature by a few modules totally irrespective of the sampling data. However existing PTQ methods do not optimize these modules separately. They adopt inappropriate reconstruction targets and complex calibration methods resulting in a severe disturbance of the temporal feature and denoising trajectory as well as a low compression efficiency. To solve these we propose a Temporal Feature Maintenance Quantization (TFMQ) framework building upon a Temporal Information Block which is just related to the time-step t and unrelated to the sampling data. Powered by the pioneering block design we devise temporal information aware reconstruction (TIAR) and finite set calibration (FSC) to align the full-precision temporal features in a limited time. Equipped with the framework we can maintain the most temporal information and ensure the end-to-end generation quality. Extensive experiments on various datasets and diffusion models prove our state-of-the-art results. Remarkably our quantization approach for the first time achieves model performance nearly on par with the full-precision model under 4-bit weight quantization. Additionally our method incurs almost no extra computational cost and accelerates quantization time by 2.0 xon LSUN-Bedrooms 256 x256 compared to previous works. Our code is publicly available at \href https://github.com/ModelTC/TFMQ-DM https://github.com/ModelTC/TFMQ-DM .

Despite their ability to generate high-resolution and diverse images from text prompts text-to-image diffusion models often suffer from slow iterative sampling processes. Model distillation is one of the most effective directions to accelerate these models. However previous distillation methods fail to retain the generation quality while requiring a significant amount of images for training either from real data or synthetically generated by the teacher model. In response to this limitation we present a novel image-free distillation scheme named SwiftBrush. Drawing inspiration from text-to-3D synthesis in which a 3D neural radiance field that aligns with the input prompt can be obtained from a 2D text-to-image diffusion prior via a specialized loss without the use of any 3D data ground-truth our approach re-purposes that same loss for distilling a pretrained multi-step text-to-image model to a student network that can generate high-fidelity images with just a single inference step. In spite of its simplicity our model stands as one of the first one-step text-to-image generators that can produce images of comparable quality to Stable Diffusion without reliance on any training image data. Remarkably SwiftBrush achieves an FID score of 16.67 and a CLIP score of 0.29 on the COCO-30K benchmark achieving competitive results or even substantially surpassing existing state-of-the-art distillation techniques.