CVPR 2024 Papers

While recent Vision-Language (VL) models excel at open-vocabulary tasks it is unclear how to use them with specific or uncommon concepts. Personalized Text-to-Image Retrieval (TIR) or Generation (TIG) are recently introduced tasks that represent this challenge where the VL model has to learn a concept from few images and respectively discriminate or generate images of the target concept in arbitrary contexts. We identify the ability to learn new meanings and their compositionality with known ones as two key properties of a personalized system. We show that the available benchmarks offer a limited validation of personalized textual concept learning from images with respect to the above properties and introduce ConCon-Chi as a benchmark for both personalized TIR and TIG designed to fill this gap. We modelled the new-meaning concepts by crafting chimeric objects and formulating a large varied set of contexts where we photographed each object. To promote the compositionality assessment of the learned concepts with known contexts we combined different contexts with the same concept and vice-versa. We carry out a thorough evaluation of state-of-the-art methods on the resulting dataset. Our study suggests that future work on personalized TIR and TIG methods should focus on the above key properties and we propose principles and a dataset for their performance assessment. Dataset: https://doi.org/10.48557/QJ1166 and code: https://github.com/hsp-iit/concon-chi_benchmark.

We study the visual semantic embedding problem for image-text matching. Most existing work utilizes a tailored cross-attention mechanism to perform local alignment across the two image and text modalities. This is computationally expensive even though it is more powerful than the unimodal dual-encoder approach. This work introduces a dual-encoder image-text matching model leveraging a scene graph to represent captions with nodes for objects and attributes interconnected by relational edges. Utilizing a graph attention network our model efficiently encodes object-attribute and object-object semantic relations resulting in a robust and fast-performing system. Representing caption as a scene graph offers the ability to utilize the strong relational inductive bias of graph neural networks to learn object-attribute and object-object relations effectively. To train the model we propose losses that align the image and caption both at the holistic level (image-caption) and the local level (image-object entity) which we show is key to the success of the model. Our model is termed Composition model for Object Relations and Attributes CORA. Experimental results on two prominent image-text retrieval benchmarks Flickr30K and MS-COCO demonstrate that CORA outperforms existing state-of-the-art computationally expensive cross-attention methods regarding recall score while achieving fast computation speed of the dual encoder. Our code is available at https://github.com/vkhoi/cora_cvpr24

Reliable hand mesh reconstruction (HMR) from commonly-used color and depth sensors is challenging especially under scenarios with varied illuminations and fast motions. Event camera is a highly promising alternative for its high dynamic range and dense temporal resolution properties but it lacks key texture appearance for hand mesh reconstruction. In this paper we propose EvRGBHand -- the first approach for 3D hand mesh reconstruction with an event camera and an RGB camera compensating for each other. By fusing two modalities of data across time space and information dimensionsEvRGBHand can tackle overexposure and motion blur issues in RGB-based HMR and foreground scarcity and background overflow issues in event-based HMR. We further propose EvRGBDegrader which allows our model to generalize effectively in challenging scenes even when trained solely on standard scenes thus reducing data acquisition costs. Experiments on real-world data demonstrate that EvRGBHand can effectively solve the challenging issues when using either type of camera alone via retaining the merits of both and shows the potential of generalization to outdoor scenes and another type of event camera. Our code models and dataset will be made public after acceptance.

Implicit neural representations (INRs) were recently proposed as a new video compression paradigm with existing approaches performing on par with HEVC. However such methods only perform well in limited settings e.g. specific model sizes fixed aspect ratios and low-motion videos. We address this issue by proposing T-NeRV a hybrid video INR that combines frame-specific embeddings with GOP-specific features providing a lever for content-specific fine-tuning. We employ entropy-constrained training to jointly optimize our model for rate and distortion and demonstrate that T-NeRV can thereby automatically adjust this lever during training effectively fine-tuning itself to the target content. We evaluate T-NeRV on the UVG dataset where it achieves state-of-the-art results on the video representation task outperforming previous works by up to 3dB PSNR on challenging high-motion sequences. Further our method improves on the compression performance of previous methods and is the first video INR to outperform HEVC on all UVG sequences.

Images captured under sub-optimal illumination conditions may contain both over- and under-exposures. We observe that over- and over-exposed regions display opposite color tone distribution shifts which may not be easily normalized in joint modeling as they usually do not have "normal-exposed" regions/pixels as reference. In this paper we propose a novel method to enhance images with both over- and under-exposures by learning to estimate and correct such color shifts. Specifically we first derive the color feature maps of the brightened and darkened versions of the input image via a UNet-based network followed by a pseudo-normal feature generator to produce pseudo-normal color feature maps. We then propose a novel COlor Shift Estimation (COSE) module to estimate the color shifts between the derived brightened (or darkened) color feature maps and the pseudo-normal color feature maps. The COSE module corrects the estimated color shifts of the over- and under-exposed regions separately. We further propose a novel COlor MOdulation (COMO) module to modulate the separately corrected colors in the over- and under-exposed regions to produce the enhanced image. Comprehensive experiments show that our method outperforms existing approaches.

nsupervised (US) video anomaly detection (VAD) in surveillance applications is gaining more popularity lately due to its practical real-world applications. Due to the extremely challenging nature of this task where learning is carried out without any annotations privacy-critical collaborative learning of US-VAD systems has not been studied yet. As surveillance videos are privacy sensitive and the availability of large-scale video data may enable better US-VAD systems collaborative learning can be highly rewarding in this setting. In this paper we propose a new baseline for anomaly detection capable of localizing anomalous events in complex surveillance scenarios in a fully unsupervised fashion without any labels on a privacy-retaining participant-based distributed training configuration. Additionally we propose three new evaluation protocols to extensively evaluate anomaly detection approaches on various scenarios of collaborations and data availability. Moreover based on these protocols we modify existing VAD datasets to extensively evaluate our approach as well as existing US SOTA methods on two large-scale datasets including UCF-Crime and XD-Violence. All proposed evaluation protocols dataset splits and codes are available here: \href https://github.com/AnasEmad11/CLAP https://github.com/AnasEmad11/CLAP .

People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs) e.g. computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails but struggle to understand and interact with GUIs thus limiting their potential to increase automation levels. In this paper we introduce CogAgent an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. By utilizing both low-resolution and high-resolution image encoders CogAgent supports input at a resolution of 1120*1120 enabling it to recognize tiny page elements and text. As a generalist visual language model CogAgent achieves the state of the art on five text-rich and four general VQA benchmarks including VQAv2 OK-VQA Text-VQA ST-VQA ChartQA infoVQA DocVQA MM-Vet and POPE. CogAgent using only screenshots as input outperforms LLM-based methods that consume extracted HTML text on both PC and Android GUI navigation tasks---Mind2Web and AITW advancing the state of the art. The model and codes are available at https://github.com/THUDM/CogVLM.

Point-spread-function (PSF) engineering is a well-established computational imaging technique that uses phase masks and other optical elements to embed extra information (e.g. depth) into the images captured by conventional CMOS image sensors. To date however PSF-engineering has not been applied to neuromorphic event cameras; a powerful new image sensing technology that responds to changes in the log-intensity of light. This paper establishes theoretical limits (Cramer Rao bounds) on 3D point localization and tracking with PSF-engineered event cameras. Using these bounds we first demonstrate that existing Fisher phase masks are already near-optimal for localizing static flashing point sources (e.g. blinking fluorescent molecules). We then demonstrate that existing designs are sub-optimal for tracking moving point sources and proceed to use our theory to design optimal phase masks and binary amplitude masks for this task. To overcome the non-convexity of the design problem we leverage novel implicit neural representation based parameterizations of the phase and amplitude masks. We demonstrate the efficacy of our designs through extensive simulations. We also validate our method with a simple prototype.

Vector-Quantized Image Modeling (VQIM) is a fundamental research problem in image synthesis which aims to represent an image with a discrete token sequence. Existing studies effectively address this problem by learning a discrete codebook from scratch and in a code-independent manner to quantize continuous representations into discrete tokens. However learning a codebook from scratch and in a code-independent manner is highly challenging which may be a key reason causing codebook collapse i.e. some code vectors can rarely be optimized without regard to the relationship between codes and good codebook priors such that die off finally. In this paper inspired by pretrained language models we find that these language models have actually pretrained a superior codebook via a large number of text corpus but such information is rarely exploited in VQIM. To this end we propose a novel codebook transfer framework with part-of-speech called VQCT which aims to transfer a well-trained codebook from pretrained language models to VQIM for robust codebook learning. Specifically we first introduce a pretrained codebook from language models and part-of-speech knowledge as priors. Then we construct a vision-related codebook with these priors for achieving codebook transfer. Finally a novel codebook transfer network is designed to exploit abundant semantic relationships between codes contained in pretrained codebooks for robust VQIM codebook learning. Experimental results on four datasets show that our VQCT method achieves superior VQIM performance over previous state-of-the-art methods.

We present CoDi-2 a Multimodal Large Language Model (MLLM) for learning in-context interleaved multimodal representations. By aligning modalities with language for both encoding and generation CoDi-2 empowers Large Language Models (LLMs) to understand modality-interleaved instructions and in-context examples and autoregressively generate grounded and coherent multimodal outputs in an any-to-any input-output modality paradigm. To train CoDi-2 we build a large-scale generation dataset encompassing in-context multimodal instructions across text vision and audio. CoDi-2 demonstrates a wide range of zero-shot and few-shot capabilities for tasks like editing exemplar learning composition reasoning etc. CoDi-2 surpasses previous domain-specific models on tasks such as subject-driven image generation vision transformation and audio editing and showcases a significant advancement for integrating diverse multimodal tasks with sequential generation.

We present the content deformation field (CoDeF) as a new type of video representation which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i.e. rendered from the canonical content field) to each individual frame along the time axis. Given a target video these two fields are jointly optimized to reconstruct it through a carefully tailored rendering pipeline. We advisedly introduce some regularizations into the optimization process urging the canonical content field to inherit semantics (e.g. the object shape) from the video. With such a design CoDeF naturally supports lifting image algorithms for video processing in the sense that one can apply an image algorithm to the canonical image and effortlessly propagate the outcomes to the entire video with the aid of the temporal deformation field. We experimentally show that CoDeF is able to lift image-to-image translation to video-to-video translation and lift keypoint detection to keypoint tracking without any training. More importantly thanks to our lifting strategy that deploys the algorithms on only one image we achieve superior cross-frame consistency in processed videos compared to existing video-to-video translation approaches and even manage to track non-rigid objects like water and smog. Code will be made publicly available.

The performance of image restoration (IR) is highly dependent on the reconstruction quality of diverse contents with varying complexity. However most IR approaches model the mapping between various complexity contents of inputs and outputs through the repeated feature calculation propagation mechanism in a unified pipeline which leads to unsatisfactory results. To address this issue we propose an explicit Content Decoupling framework for IR dubbed CoDe to end-to-end model the restoration process by utilizing decoupled content components in a divide-and-conquer-like architecture. Specifically a Content Decoupling Module is first designed to decouple content components of inputs and outputs according to the frequency spectra adaptively generated from the transform domain. In addition in order to harness the divide-and-conquer strategy for reconstructing decoupled content components we propose an IR Network Container. It contains an optimized version which is a streamlining of an arbitrary IR network comprising the cascaded modulated subnets and a Reconstruction Layers Pool. Finally a Content Consistency Loss is designed from the transform domain perspective to supervise the restoration process of each content component and further guide the feature fusion process. Extensive experiments on several IR tasks such as image super-resolution image denoising and image blurring covering both real and synthetic settings demonstrate that the proposed paradigm can effectively take the performance of the original network to a new state-of-the-art level in multiple benchmark datasets (e.g. 0.34dB@Set5 x4 over DAT).

Prominent solutions for medical image segmentation are typically tailored for automatic or interactive setups posing challenges in facilitating progress achieved in one task to another. This also necessitates separate models for each task duplicating both training time and parameters. To address above issues we introduce S2VNet a universal framework that leverages Slice-to-Volume propagation to unify automatic/interactive segmentation within a single model and one training session. Inspired by clustering-based segmentation techniques S2VNet makes full use of the slice-wise structure of volumetric data by initializing cluster centers from the cluster results of previous slice. This enables knowledge acquired from prior slices to assist in the segmentation of the current slice further efficiently bridging the communication between remote slices using mere 2D networks. Moreover such a framework readily accommodates inter- active segmentation with no architectural change simply by initializing centroids from user inputs. S2VNet distinguishes itself by swift inference speeds and reduced memory consumption compared to prevailing 3D solutions. It can also handle multi-class interactions with each of them serving to initialize different centroids. Experiments on three benchmarks demonstrate S2VNet surpasses task-specified solutions on both automatic/interactive setups.

The burgeoning field of Multimodal Large Language Models (MLLMs) has exhibited remarkable performance in diverse tasks such as captioning commonsense reasoning and visual scene understanding. However the deployment of these large-scale MLLMs on client devices is hindered by their extensive model parameters leading to a notable decline in generalization capabilities when these models are compressed for device deployment. Addressing this challenge we introduce a Cloud-Device Collaborative Continual Adaptation framework designed to enhance the performance of compressed device-deployed MLLMs by leveraging the robust capabilities of cloud-based larger-scale MLLMs. Our framework is structured into three key components: a device-to-cloud uplink for efficient data transmission cloud-based knowledge adaptation and an optimized cloud-to-device downlink for model deployment. In the uplink phase we employ an Uncertainty-guided Token Sampling (UTS) strategy to effectively filter out-of-distribution tokens thereby reducing transmission costs and improving training efficiency. On the cloud side we propose Adapter-based Knowledge Distillation (AKD) method to transfer refined knowledge from large-scale to compressed pocket-size MLLMs. Furthermore we propose a Dynamic Weight update Compression (DWC) strategy for the downlink which adaptively selects and quantizes updated weight parameters enhancing transmission efficiency and reducing the representational disparity between cloud and device models. Extensive experiments on several multimodal benchmarks demonstrate the superiority of our proposed framework over prior Knowledge Distillation and device-cloud collaboration methods. Notably we also validate the feasibility of our approach to real-world experiments.

We introduce ChatPose a framework employing Large Language Models (LLMs) to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated by the human ability to intuitively understand postures from a single image or a brief description a process that intertwines image interpretation world knowledge and an understanding of body language. Traditional human pose estimation and generation methods often operate in isolation lacking semantic understanding and reasoning abilities. ChatPose addresses these limitations by embedding SMPL poses as distinct signal tokens within a multimodal LLM enabling the direct generation of 3D body poses from both textual and visual inputs. Leveraging the powerful capabilities of multimodal LLMs ChatPose unifies classical 3D human pose and generation tasks while offering user interactions. Additionally ChatPose empowers LLMs to apply their extensive world knowledge in reasoning about human poses leading to two advanced tasks: speculative pose generation and reasoning about pose estimation. These tasks involve reasoning about humans to generate 3D poses from subtle text queries possibly accompanied by images. We establish benchmarks for these tasks moving beyond traditional 3D pose generation and estimation methods. Our results show that ChatPose out-performs existing multimodal LLMs and task-specific methods on these newly proposed tasks. Furthermore ChatPose's ability to understand and generate 3D human poses based on complex reasoning opens new directions in human pose analysis. Code and data are available for research at https://yfeng95.github.io/ChatPose.

Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multimodal conversations. However existing methods encounter challenges in effectively handling both image and video understanding particularly with limited visual tokens. In this work we introduce Chat-UniVi a Unified Vision-language model capable of comprehending and engaging in conversations involving images and videos through a unified visual representation. Specifically we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to efficiently utilize a limited number of visual tokens to simultaneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover we leverage a multi-scale representation enabling the model to perceive both high-level semantic concepts and low-level visual details. Notably Chat-UniVi is trained on a mixed dataset containing both images and videos allowing direct application to tasks involving both mediums without requiring any modifications. Extensive experimental results demonstrate that Chat-UniVi consistently outperforms even existing methods exclusively designed for either images or videos. Code is available at https://github.com/PKU-YuanGroup/Chat-UniVi.

Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success but suffer from excessive noise. Recent studies use alternative captions synthesized by captioning models and have achieved notable benchmark performance. However our experiments reveal significant Scalability Deficiency and World Knowledge Loss issues in models trained with synthetic captions which have been largely obscured by their initial benchmark success. Upon closer examination we identify the root cause as the overly-simplified language structure and lack of knowledge details in existing synthetic captions. To provide higher-quality and more scalable multimodal pretraining data we propose CapsFusion an advanced framework that leverages large language models to consolidate and refine information from both web-based image-text pairs and synthetic captions. Extensive experiments show that CapsFusion captions exhibit remarkable all-round superiority over existing captions in terms of model performance (e.g. 18.8 and 18.3 improvements in CIDEr score on COCO and NoCaps) sample efficiency (requiring 11-16 times less computation than baselines) world knowledge depth and scalability. These effectiveness efficiency and scalability advantages position CapsFusion as a promising candidate for future scaling of LMM training.

Language models have demonstrated impressive ability in context understanding and generative performance. Inspired by the recent success of language foundation models in this paper we propose LMTraj (Language-based Multimodal Trajectory predictor) which recasts the trajectory prediction task into a sort of question-answering problem. Departing from traditional numerical regression models which treat the trajectory coordinate sequence as continuous signals we consider them as discrete signals like text prompts. Specially we first transform an input space for the trajectory coordinate into the natural language space. Here the entire time-series trajectories of pedestrians are converted into a text prompt and scene images are described as text information through image captioning. The transformed numerical and image data are then wrapped into the question-answering template for use in a language model. Next to guide the language model in understanding and reasoning high-level knowledge such as scene context and social relationships between pedestrians we introduce an auxiliary multi-task question and answering. We then train a numerical tokenizer with the prompt data. We encourage the tokenizer to separate the integer and decimal parts well and leverage it to capture correlations between the consecutive numbers in the language model. Lastly we train the language model using the numerical tokenizer and all of the question-answer prompts. Here we propose a beam-search-based most-likely prediction and a temperature-based multimodal prediction to implement both deterministic and stochastic inferences. Applying our LMTraj we show that the language-based model can be a powerful pedestrian trajectory predictor and outperforms existing numerical-based predictor methods. Extensive experiments show that our LMTraj can successfully understand social relationships and accurately extrapolate the multimodal futures on the public pedestrian trajectory prediction benchmark. Code is publicly available at https://github.com/inhwanbae/LMTrajectory.