CVPR 2024 Papers

With photo-realistic image generation Neural Radiance Field (NeRF) is widely used for large-scale dynamic scene reconstruction as autonomous driving simulator. However large-scale scene reconstruction still suffers from extremely long training time and rendering time. Low-resolution (LR) rendering combined with upsampling can alleviate this problem but it degrades image quality. In this paper we design a lightweight reference decoder which exploits prior information from known views to improve image reconstruction quality of new views. In addition to speed up prior information search we propose an optical flow and structural similarity based prior information search method. Results on KITTI and VKITTI2 datasets show that our method significantly outperforms the baseline method in terms of training speed rendering speed and rendering quality.

Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector followed by different temporal aggregation methods. However these approaches require per-frame objects or whole point clouds posing challenges related to memory bank utilization. Moreover point clouds and trajectory features are combined solely based on concatenation which may neglect effective interactions between them. In this paper we propose a point-trajectory transformer with long short-term memory for efficient temporal 3D object detection. To this end we only utilize point clouds of current-frame objects and their historical trajectories as input to minimize the memory bank storage requirement. Furthermore we introduce modules to encode trajectory features focusing on long short-term and future-aware perspectives and then effectively aggregate them with point cloud features. We conduct extensive experiments on the large-scale Waymo dataset to demonstrate that our approach performs well against state-of-the-art methods. The source codes and trained models will be made publicly available. Code and models will be made publicly available at https://github.com/kuanchihhuang/PTT.

Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However as a large-scale model the immense memory and computation costs hinder its practical deployment. In this paper we propose a post-training quantization (PTQ) framework for Segment Anything Model namely PTQ4SAM. First we investigate the inherent bottleneck of SAM quantization attributed to the bimodal distribution in \cls post-Key-Linear activations. We analyze its characteristics from both per-tensor and per-channel perspectives and propose a Bimodal Integration strategy which utilizes a mathematically equivalent sign operation to transform the bimodal distribution into a relatively easy-quantized normal distribution offline. Second SAM encompasses diverse attention mechanisms (i.e. self-attention and two-way cross-attention) resulting in substantial variations in the post-Softmax distributions. Therefore we introduce an Adaptive Granularity Quantization for Softmax through searching the optimal power-of-two base which is hardware-friendly. Extensive experimental results across various vision tasks (instance segmentation semantic segmentation and object detection) datasets and model variants show the superiority of PTQ4SAM. For example when quantizing SAM-L to 6-bit we achieve lossless accuracy for instance segmentation about 0.5% drop with theoretical 3.9xacceleration. The code is available at https://github.com/chengtao-lv/PTQ4SAM.

Video quality assessment (VQA) is a challenging problem due to the numerous factors that can affect the perceptual quality of a video e.g. content attractiveness distortion type motion pattern and level. However annotating the Mean opinion score (MOS) for videos is expensive and time-consuming which limits the scale of VQA datasets and poses a significant obstacle for deep learning-based methods. In this paper we propose a VQA method named PTM-VQA which leverages PreTrained Models to transfer knowledge from models pretrained on various pre-tasks enabling benefits for VQA from different aspects. Specifically we extract features of videos from different pretrained models with frozen weights and integrate them to generate representation. Since these models possess various fields of knowledge and are often trained with labels irrelevant to quality we propose an Intra-Consistency and Inter-Divisibility (ICID) loss to impose constraints on features extracted by multiple pretrained models. The intra-consistency constraint ensures that features extracted by different pretrained models are in the same unified quality-aware latent space while the inter-divisibility introduces pseudo clusters based on the annotation of samples and tries to separate features of samples from different clusters. Furthermore with a constantly growing number of pretrained models it is crucial to determine which models to use and how to use them. To address this problem we propose an efficient scheme to select suitable candidates. Models with better clustering performance on VQA datasets are chosen to be our candidates. Extensive experiments demonstrate the effectiveness of the proposed method.

Image-level Weakly Supervised Semantic Segmentation (WSSS) has received increasing attention due to its low annotation cost. Class Activation Mapping (CAM) generated through classifier weights in WSSS inevitably ignores certain useful cues while the CAM generated through class prototypes can alleviate that. However because of the different goals of image classification and semantic segmentation the class prototypes still focus on activating primary discriminative pixels learned from classification loss leading to incomplete CAM. In this paper we propose a plugand-play Prototype-based Secondary Discriminative Pixels Mining (PSDPM) framework for enabling class prototypes to activate more secondary discriminative pixels thus generating a more complete CAM. Specifically we introduce a Foreground Pixel Estimation Module (FPEM) for estimating potential foreground pixels based on the correlations between primary and secondary discriminative pixels and the semantic segmentation results of baseline methods. Then we enable WSSS model to learn discriminative features from secondary discriminative pixels through a consistency loss calculated between FPEM result and class-prototype CAM. Experimental results show that our PSDPM improves various baseline methods significantly and achieves new state-of-the-art performances on WSSS benchmarks. Codes are available at https://github.com/xinqiaozhao/PSDPM.

Promptly identifying procedural errors from egocentric videos in an online setting is highly challenging and valuable for detecting mistakes as soon as they happen. This capability has a wide range of applications across various fields such as manufacturing and healthcare. The nature of procedural mistakes is open-set since novel types of failures might occur which calls for one-class classifiers trained on correctly executed procedures. However no technique can currently detect open-set procedural mistakes online. We propose PREGO the first online one-class classification model for mistake detection in PRocedural EGOcentric videos. PREGO is based on an online action recognition component to model the current action and a symbolic reasoning module to predict the next actions. Mistake detection is performed by comparing the recognized current action with the expected future one. We evaluate PREGO on two procedural egocentric video datasets Assembly101 and Epic-tent which we adapt for online benchmarking of procedural mistake detection to establish suitable benchmarks thus defining the Assembly101-O and Epic-tent-O datasets respectively. The code is available at https://github.com/aleflabo/PREGO

Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize rewards that reflect human preference. However in the vision domain existing RL-based reward finetuning methods are limited by their instability in large-scale training rendering them incapable of generalizing to complex unseen prompts. In this paper we propose Proximal Reward Difference Prediction (PRDP) enabling stable black-box reward finetuning for diffusion models for the first time on large-scale prompt datasets with over 100K prompts. Our key innovation is the Reward Difference Prediction (RDP) objective that has the same optimal solution as the RL objective while enjoying better training stability. Specifically the RDP objective is a supervised regression objective that tasks the diffusion model with predicting the reward difference of generated image pairs from their denoising trajectories. We theoretically prove that the diffusion model that obtains perfect reward difference prediction is exactly the maximizer of the RL objective. We further develop an online algorithm with proximal updates to stably optimize the RDP objective. In experiments we demonstrate that PRDP can match the reward maximization ability of well-established RL-based methods in small-scale training. Furthermore through large-scale training on text prompts from the Human Preference Dataset v2 and the Pick-a-Pic v1 dataset PRDP achieves superior generation quality on a diverse set of complex unseen prompts whereas RL-based methods completely fail.

Generating dances that are both lifelike and well-aligned with music continues to be a challenging task in the cross-modal domain. This paper introduces PopDanceSet the first dataset tailored to the preferences of young audiences enabling the generation of aesthetically oriented dances. And it surpasses the AIST++ dataset in music genre diversity and the intricacy and depth of dance movements. Moreover the proposed POPDG model within the iDDPM framework enhances dance diversity and through the Space Augmentation Algorithm strengthens spatial physical connections between human body joints ensuring that increased diversity does not compromise generation quality. A streamlined Alignment Module is also designed to improve the temporal alignment between dance and music. Extensive experiments show that POPDG achieves SOTA results on two datasets. Furthermore the paper also expands on current evaluation metrics. The dataset and code are available at https://github.com/Luke-Luo1/POPDG.

Multi-constraint offline reinforcement learning (RL) promises to learn policies that satisfy both cumulative and state-wise costs from offline datasets. This arrangement provides an effective approach for the widespread application of RL in high-risk scenarios where both cumulative and state-wise costs need to be considered simultaneously. However previously constrained offline RL algorithms are primarily designed to handle single-constraint problems related to cumulative cost which faces challenges when addressing multi-constraint tasks that involve both cumulative and state-wise costs. In this work we propose a novel Primal policy Optimization with Conservative Estimation algorithm (POCE) to address the problem of multi-constraint offline RL. Concretely we reframe the objective of multi-constraint offline RL by introducing the concept of Maximum Markov Decision Processes (MMDP). Subsequently we present a primal policy optimization algorithm to confront the multi-constraint problems which improves the stability and convergence speed of model training. Furthermore we propose a conditional Bellman operator to estimate cumulative and state-wise Q-values reducing the extrapolation error caused by out-of-distribution (OOD) actions. Finally extensive experiments demonstrate that the POCE algorithm achieves competitive performance across multiple experimental tasks particularly outperforming baseline algorithms in terms of safety. Our code is available at \href https://github.com/guanjiayi/poce github.POCE .

The primary focus of Neural Representation for Videos (NeRV) is to effectively model its spatiotemporal consistency. However current NeRV systems often face a significant issue of spatial inconsistency leading to decreased perceptual quality. To address this issue we introduce the Pyramidal Neural Representation for Videos (PNeRV) which is built on a multi-scale information connection and comprises a lightweight rescaling operator Kronecker Fully-connected layer (KFc) and a Benign Selective Memory (BSM) mechanism. The KFc inspired by the tensor decomposition of the vanilla Fully-connected layer facilitates low-cost rescaling and global correlation modeling. BSM merges high-level features with granular ones adaptively. Furthermore we provide an analysis based on the Universal Approximation Theory of the NeRV system and validate the effectiveness of the proposed PNeRV. We conducted comprehensive experiments to demonstrate that PNeRV surpasses the performance of contemporary NeRV models achieving the best results in video regression on UVG and DAVIS under various metrics (PSNR SSIM LPIPS and FVD). Compared to vanilla NeRV PNeRV achieves a +4.49 dB gain in PSNR and a 231% increase in FVD on UVG along with a +3.28 dB PSNR and 634% FVD increase on DAVIS.

Neural implicit scene representations have recently shown encouraging results in dense visual SLAM. However existing methods produce low-quality scene reconstruction and low-accuracy localization performance when scaling up to large indoor scenes and long sequences. These limitations are mainly due to their single global radiance field with finite capacity which does not adapt to large scenarios. Their end-to-end pose networks are also not robust enough with the growth of cumulative errors in large scenes. To this end we introduce PLGSLAM a neural visual SLAM system capable of high-fidelity surface reconstruction and robust camera tracking in real-time. To handle large-scale indoor scenes PLGSLAM proposes a progressive scene representation method which dynamically allocates new local scene representation trained with frames within a local sliding window. This allows us to scale up to larger indoor scenes and improves robustness (even under pose drifts). In local scene representation PLGSLAM utilizes tri-planes for local high-frequency features with multi-layer perceptron (MLP) networks for the low-frequency feature achieving smoothness and scene completion in unobserved areas. Moreover we propose local-to-global bundle adjustment method with a global keyframe database to address the increased pose drifts on long sequences. Experimental results demonstrate that PLGSLAM achieves state-of-the-art scene reconstruction results and tracking performance across various datasets and scenarios (both in small and large-scale indoor environments).

Recent advancements in large-scale pre-trained text-to-image models have led to remarkable progress in semantic image synthesis. Nevertheless synthesizing high-quality images with consistent semantics and layout remains a challenge. In this paper we propose the adaPtive LAyout-semantiC fusion modulE (PLACE) that harnesses pre-trained models to alleviate the aforementioned issues. Specifically we first employ the layout control map to faithfully represent layouts in the feature space. Subsequently we combine the layout and semantic features in a timestep-adaptive manner to synthesize images with realistic details. During fine-tuning we propose the Semantic Alignment (SA) loss to further enhance layout alignment. Additionally we introduce the Layout-Free Prior Preservation (LFP) loss which leverages unlabeled data to maintain the priors of pre-trained models thereby improving the visual quality and semantic consistency of synthesized images. Extensive experiments demonstrate that our approach performs favorably in terms of visual quality semantic consistency and layout alignment. The source code and model are available at \href https://github.com/cszy98/PLACE/tree/main PLACE .

High-quality human reconstruction and photo-realistic rendering of a dynamic scene is a long-standing problem in computer vision and graphics. Despite considerable efforts invested in developing various capture systems and reconstruction algorithms recent advancements still struggle with loose or oversized clothing and overly complex poses. In part this is due to the challenges of acquiring high-quality human datasets. To facilitate the development of these fields in this paper we present PKU-DyMVHumans a versatile human-centric dataset for high-fidelity reconstruction and rendering of dynamic human scenarios from dense multi-view videos. It comprises 8.2 million frames captured by more than 56 synchronized cameras across diverse scenarios. These sequences comprise 32 human subjects across 45 different scenarios each with a high-detailed appearance and realistic human motion. Inspired by recent advancements in neural radiance field (NeRF)-based scene representations we carefully set up an off-the-shelf framework that is easy to provide those state-of-the-art NeRF-based implementations and benchmark on PKU-DyMVHumans dataset. It is paving the way for various applications like fine-grained foreground/background decomposition high-quality human reconstruction and photo-realistic novel view synthesis of a dynamic scene. Extensive studies are performed on the benchmark demonstrating new observations and challenges that emerge from using such high-fidelity dynamic data. The project page and data is available at: https://pku-dymvhumans.github.io.

Vision-Language Models (VLMs) such as Flamingo and GPT-4V have shown immense potential by integrating large language models with vision systems. Nevertheless these models face challenges in the fundamental computer vision task of object localisation due to their training on multimodal data containing mostly captions without explicit spatial grounding. While it is possible to construct custom supervised training pipelines with bounding box annotations that integrate with VLMs these result in specialized and hard-to-scale models. In this paper we aim to explore the limits of caption-based VLMs and instead propose to tackle the challenge in a simpler manner by i) keeping the weights of a caption-based VLM frozen and ii) not using any supervised detection data. To this end we introduce an input-agnostic Positional Insert (PIN) a learnable spatial prompt containing a minimal set of parameters that are slid inside the frozen VLM unlocking object localisation capabilities. Our PIN module is trained with a simple next-token prediction task on synthetic data without requiring the introduction of new output heads. Our experiments demonstrate strong zero-shot localisation performances on a variety of images including Pascal VOC COCO LVIS and diverse images like paintings or cartoons.

Planet-scale image geolocalization remains a challenging problem due to the diversity of images originating from anywhere in the world. Although approaches based on vision transformers have made significant progress in geolocalization accuracy success in prior literature is constrained to narrow distributions of images of landmarks and performance has not generalized to unseen places. We present a new geolocalization system that combines semantic geocell creation multi-task contrastive pretraining and a novel loss function. Additionally our work is the first to perform retrieval over location clusters for guess refinements. We train two models for evaluations on street-level data and general-purpose image geolocalization; the first model PIGEON is trained on data from the game of GeoGuessr and is capable of placing over 40% of its guesses within 25 kilometers of the target location globally. We also develop a bot and deploy PIGEON in a blind experiment against humans ranking in the top 0.01% of players. We further challenge one of the world's foremost professional GeoGuessr players to a series of six matches with millions of viewers winning all six games. Our second model PIGEOTTO differs in that it is trained on a dataset of images from Flickr and Wikipedia achieving state-of-the-art results on a wide range of image geolocalization benchmarks outperforming the previous SOTA by up to 7.7 percentage points on the city accuracy level and up to 38.8 percentage points on the country level. Our findings suggest that PIGEOTTO is the first image geolocalization model that effectively generalizes to unseen places and that our approach can pave the way for highly accurate planet-scale image geolocalization systems. Our code is available on GitHub.

We show that physics-based simulations can be seamlessly integrated with NeRF to generate high-quality elastodynamics of real-world objects. Unlike existing methods we discretize nonlinear hyperelasticity in a meshless way obviating the necessity for intermediate auxiliary shape proxies like a tetrahedral mesh or voxel grid. A quadratic generalized moving least square is employed to capture nonlinear dynamics and large deformation on the implicit model. Such meshless integration enables versatile simulations of complex and codimensional shapes. We adaptively place the least-square kernels according to the NeRF density field to significantly reduce the complexity of the nonlinear simulation. As a result physically realistic animations can be conveniently synthesized using our method for a wide range of hyperelastic materials at an interactive rate. For more information please visit https://fytalon.github.io/pienerf.

In this paper we propose a novel virtual try-on from unconstrained designs (ucVTON) task to enable photorealistic synthesis of personalized composite clothing on input human images. Unlike prior arts constrained by specific input types our method allows flexible specification of style (text or image) and texture (full garment cropped sections or texture patches) conditions. To address the entanglement challenge when using full garment images as conditions we develop a two-stage pipeline with explicit disentanglement of style and texture. In the first stage we generate a human parsing map reflecting the desired style conditioned on the input. In the second stage we composite textures onto the parsing map areas based on the texture input. To represent complex and non-stationary textures that have never been achieved in previous fashion editing works we first propose extracting hierarchical and balanced CLIP features and applying position encoding in VTON. Experiments demonstrate superior synthesis quality and personalization enabled by our method. The flexible control over style and texture mixing brings virtual try-on to a new level of user experience for online shopping and fashion design.

Recent advancements in personalized text-to-image (T2I) models have revolutionized content creation empowering non-experts to generate stunning images with unique styles. While promising animating these personalized images with realistic motions poses significant challenges in preserving distinct styles high-fidelity details and achieving motion controllability by text. In this paper we present PIA a Personalized Image Animator that excels in aligning with condition images achieving motion controllability by text and the compatibility with various personalized T2I models without specific tuning. To achieve these goals PIA builds upon a base T2I model with well-trained temporal alignment layers allowing for the seamless transformation of any personalized T2I model into an image animation model. A key component of PIA is the introduction of the condition module which takes as inputs the condition frame and inter-frame affinity. This module leverages the affinity hint to transfer appearance information from the condition frame to individual frames in the latent space. This design mitigates the challenges of appearance-related frame alignment within PIA and allows for a stronger focus on aligning with motion-related guidance. To address the lack of a benchmark for this field we introduce AnimateBench a comprehensive benchmark comprising diverse personalized T2I models curated images and motion-related prompts. We show extensive evaluations and applications on AnimateBench to verify the superiority of PIA.

Diffusion models trained on large-scale text-image datasets have demonstrated a strong capability of controllable high-quality image generation from arbitrary text prompts. However the generation quality and generalization ability of 3D diffusion models is hindered by the scarcity of high-quality and large-scale 3D datasets. In this paper we present PI3D a framework that fully leverages the pre-trained text-to-image diffusion models' ability to generate high-quality 3D shapes from text prompts in minutes. The core idea is to connect the 2D and 3D domains by representing a 3D shape as a set of Pseudo RGB Images. We fine-tune an existing text-to-image diffusion model to produce such pseudo-images using a small number of text-3D pairs. Surprisingly we find that it can already generate meaningful and consistent 3D shapes given complex text descriptions. We further take the generated shapes as the starting point for a lightweight iterative refinement using score distillation sampling to achieve high-quality generation under a low budget. PI3D generates a single 3D shape from text in only 3 minutes and the quality is validated to outperform existing 3D generative models by a large margin.