ECCV 2024 Papers

"To advance the state of the art in the creation of 3D foundation models, this paper introduces the framework for 3D pre-training utilizing existing pre-trained 2D networks and large-scale multi-view datasets. We propose a novel 2D-3D joint training scheme to extract co-embedded 2D and 3D features in an end-to-end pipeline, where 2D-3D feature consistency is enforced through a volume rendering NeRF-like ray marching process. Using dense per pixel features we are able to 1) directly distill the learned priors from 2D models to 3D models and create useful 3D backbones, 2) extract more consistent and less noisy 2D features, 3) formulate a consistent embedding space where 2D, 3D, and other modalities of data (e.g., natural language prompts) can be jointly queried. Furthermore, besides dense features, can be trained to extract sparse features (e.g., key points), also with 2D-3D consistency – condensing 3D NeRF representations into compact sets of decorated key points. We demonstrate that our pre-trained model provides good initialization for various 3D tasks including 3D classification and segmentation, outperforming other 3D pre-training methods by a significant margin. It also enables, by exploiting our sparse features, additional useful downstream tasks, such as matching 2D images to 3D scenes, detecting duplicate 3D scenes, and querying a repository of 3D scenes through natural language – all quite efficiently and without any per-scene fine-tuning."

"The linear inverse problem associated with the standard model for hyperspectral image recovery from CASSI measurements is considered. This is formulated as the minimization of an objective function which is the sum of a total variation regularizer and a least squares loss function. Standard first-order iterative minimization algorithms, such as ISTA, FISTA and TwIST, require as input the value of the Lipschitz constant for the gradient of the loss function, or at least a good upper bound on this value, in order to select appropriate step lengths. For the loss term considered here, this Lipschitz constant equals the square of the largest singular value of the measurement map. In applications, this number is usually computed directly as the largest eigenvalue of a huge square matrix. This can sometimes become a bottleneck in an otherwise optimized algorithm. In the present paper we effectively eliminate this bottleneck for CASSI reconstructions by showing how the Lipschitz constant can be calculated from a square matrix whose size is easily three orders of magnitudes smaller than in the direct approach."

"3D generation has witnessed significant advancements, yet efficiently producing high-quality 3D assets from a single image remains challenging. In this paper, we present a triplane autoencoder, which encodes 3D models into a compact triplane latent space to effectively compress both the 3D geometry and texture information. Within the autoencoder framework, we introduce a 3D-aware cross-attention mechanism, which utilizes low-resolution latent representations to query features from a high-resolution 3D feature volume, thereby enhancing the representation capacity of the latent space. Subsequently, we train a diffusion model on this refined latent space. In contrast to solely relying on image embedding for 3D generation, our proposed method advocates for the simultaneous utilization of both image embedding and shape embedding as conditions. Specifically, the shape embedding is estimated via a diffusion prior model conditioned on the image embedding. Through comprehensive experiments, we demonstrate that our method outperforms state-of-the-art algorithms, achieving superior performance while requiring less training data and time. Our approach enables the generation of high-quality 3D assets in merely 7 seconds on a single A100 GPU. More results and visualization can be found on our project page: https://compress3d.github.io/."

"As deep vision models’ popularity rapidly increases, there is a growing emphasis on explanations for model predictions. The inherently explainable attribution method aims to enhance the understanding of model behavior by identifying the important regions in images that significantly contribute to predictions. It is achieved by cooperatively training a selector (generating an attribution map to identify important features) and a predictor (making predictions using the identified features). Despite many advancements, existing methods suffer from the incompleteness problem, where discriminative features are masked out, and the interlocking problem, where the non-optimized selector initially selects noise, causing the predictor to fit on this noise and perpetuate the cycle. To address these problems, we introduce a new objective that discourages the presence of discriminative features in the masked-out regions thus enhancing the comprehensiveness of feature selection. A pre-trained detector is introduced to detect discriminative features in the masked-out region. If the selector selects noise instead of discriminative features, the detector can observe and break the interlocking situation by penalizing the selector. Extensive experiments show that our model makes accurate predictions with higher accuracy than the regular black-box model, and produces attribution maps with high feature coverage, localization ability, fidelity and robustness. Our code will be available at https://github.com/Zood123/COMET."

"Compositional generalization has received much attention in vision-and-language and visual reasoning recently. Substitutivity, the capability to generalize to novel compositions with synonymous primitives such as words and visual entities, is an essential factor in evaluating the compositional generalization ability but remains largely unexplored. In this paper, we explore the compositional substitutivity of visual reasoning in the context of visual question answering (VQA). We propose a training framework for VQA models to maintain compositional substitutivity. The basic idea is to learn invariant representations for synonymous primitives via support-sets. Specifically, for each question-image pair, we construct a support question set and a support image set, and both sets contain questions/images that share synonymous primitives with the original question/image. By enforcing a VQA model to reconstruct the original question/image with the sets, the model is able to identify which primitives are synonymous. To quantitatively evaluate the substitutivity of VQA models, we introduce two datasets: GQA-SPS and VQA-SPS v2, by performing three types of substitutions using synonymous primitives including words, visual entities, and referents. Experimental results demonstrate the effectiveness of our framework. We release GQA-SPS and VQA-SPS v2 at https://github.com/NeverMoreLCH/CG-SPS."

"Diffusion models achieve remarkable quality in image generation, but at a cost. Iterative denoising requires many time steps to produce high fidelity images. The denoising process is crucially limited by an accumulation of the reconstruction error due to an initial inaccurate reconstruction of the target data. This leads to lower quality outputs, and slower convergence. To address these issues, we propose compensation sampling to guide the generation towards the target domain. We introduce a compensation term, implemented as a U-Net, which adds negligible training overhead. Our approach is flexible and we demonstrate its application in unconditional generation, face inpainting, and face de-occlusion on benchmark datasets CIFAR-10, CelebA, CelebA-HQ, FFHQ-256, and FSG. Our approach consistently yields state-of-the-art results in terms of image quality, while accelerating the denoising process to converge during training by up to an order of magnitude."

"3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast rendering at high-quality. However, the storage size is significantly higher, which hinders practical deployment, e.g. on resource constrained devices. In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering. Central to our idea is the explicit exploitation of perceptual redundancies present in natural scenes. In essence, the inherent nature of a scene allows for numerous permutations of Gaussian parameters to equivalently represent it. To this end, we propose a novel highly parallel algorithm that regularly arranges the high-dimensional Gaussian parameters into a 2D grid while preserving their neighborhood structure. During training, we further enforce local smoothness between the sorted parameters in the grid. The uncompressed Gaussians use the same structure as 3DGS, ensuring a seamless integration with established renderers. Our method achieves a reduction factor of 17x to 42x in size for complex scenes with no increase in training time, marking a substantial leap forward in the domain of 3D scene distribution and consumption. Additional information can be found on our project page: fraunhoferhhi.github.io/Self-Organizing-Gaussians/"

"3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the parameters for several 3D Gaussians. We notice that many Gaussians may share similar parameters, so we introduce a simple vector quantization method based on to quantize the Gaussian parameters while optimizing them. Then, we store the small codebook along with the index of the code for each Gaussian. We compress the indices further by sorting them and using a method similar to run-length encoding. Moreover, we use a simple regularizer to encourage zero opacity (invisible Gaussians) to reduce the storage and rendering time by a large factor through reducing the number of Gaussians. We do extensive experiments on standard benchmarks as well as an existing 3D dataset that is an order of magnitude larger than the standard benchmarks used in this field. We show that our simple yet effective method can reduce the storage cost for 3DGS by 40× to 50× and rendering time by 2× to 3× with a very small drop in the quality of rendered images. Our code is available here: https://github.com/UCDvision/compact3d"

"Images tell stories, trigger emotions, and let us recall memories – they make us think. Thus, they have the ability to attract and hold one’s attention, which is the definition of being “interesting”. Yet, the appeal of an image is highly subjective. Looking at the image of my son taking his first steps will always bring me back to this emotional moment, while it is just a blurry, quickly taken snapshot to most others. Preferences vary widely: some adore cats, others are dog enthusiasts, and a third group may not be fond of either. We argue that every image can be interesting to a particular observer under certain circumstances. This work particularly emphasizes subjective preferences. However, our analysis of 2.5k image collections from diverse users of the photo-sharing platform Flickr reveals that specific image characteristics make them commonly more interesting. For instance, images, including professionally taken landscapes, appeal broadly due to their aesthetic qualities. In contrast, subjectively interesting images, such as those depicting personal or niche community events, resonate on a more individual level, often evoking personal memories and emotions."

"State-of-the-art deepfake detection approaches rely on image-based features extracted via neural networks. While these approaches trained in a supervised manner extract likely fake features, they may fall short in representing unnatural ‘non-physical’ semantic facial attributes – blurry hairlines, double eyebrows, rigid eye pupils, or unnatural skin shading. However, such facial attributes are easily perceived by humans and used to discern the authenticity of an image based on human common sense. Furthermore, image-based feature extraction methods that provide visual explanations via saliency maps can be hard to interpret for humans. To address these challenges, we frame deepfake detection as a Deepfake Detection VQA (DD-VQA) task and model human intuition by providing textual explanations that describe common sense reasons for labeling an image as real or fake. We introduce a new annotated dataset and propose a Vision and Language Transformer-based framework for the DD-VQA task. We also incorporate text and image-aware feature alignment formulation to enhance multi-modal representation learning. As a result, we improve upon existing deepfake detection models by integrating our learned vision representations, which reason over common sense knowledge from the DD-VQA task. We provide extensive empirical results demonstrating that our method enhances detection performance, generalization ability, and language-based interpretability in the deepfake detection task. Our dataset is available at https://github.com/Reality-Defender/Research-DD-VQA."

"Generating high-quality 3D assets from a given image is highly desirable in various applications such as AR/VR. Recent advances in single-image 3D generation explore feed-forward models that learn to infer the 3D model of an object without optimization. Though promising results have been achieved in single object generation, these methods often struggle to model complex 3D assets that inherently contain multiple objects. In this work, we present ComboVerse, a 3D generation framework that produces high-quality 3D assets with complex compositions by learning to combine multiple models. 1) We first perform an in-depth analysis of this “multi-object gap” from both model and data perspectives. 2) Next, with reconstructed 3D models of different objects, we seek to adjust their sizes, rotation angles, and locations to create a 3D asset that matches the given image. 3) To automate this process, we apply spatially-aware score distillation sampling (SSDS) from pretrained diffusion models to guide the positioning of objects. Our proposed framework emphasizes spatial alignment of objects, compared with standard score distillation sampling, and thus achieves more accurate results. Extensive experiments validate ComboVerse achieves clear improvements over existing methods in generating compositional 3D assets."

"Wide-angle lens distortion in portrait photography presents a significant challenge for capturing photo-realistic and aesthetically pleasing images. Such distortions are especially noticeable in facial regions. In this work, we propose encapsulating the generative face prior as a guided natural manifold to facilitate the correction of facial regions. Moreover, a notable central symmetry relationship exists in the non-face background, yet it has not been explored in the correction process. This geometry prior motivates us to introduce a novel constraint to explicitly enforce symmetry throughout the correction process, thereby contributing to a more visually appealing and natural correction in the non-face region. Experiments demonstrate that our approach outperforms previous methods by a large margin, excelling not only in quantitative measures such as line straightness and shape consistency metrics but also in terms of perceptual visual quality. All the code and models are available at https://github.com/ Dev-Mrha/DualPriorsCorrection."

"Recent progress in personalizing text-to-image (T2I) diffusion models has demonstrated their capability to generate images based on personalized visual concepts using only a few user-provided examples. However, these models often struggle with maintaining high visual fidelity, particularly when modifying scenes according to textual descriptions. To address this challenge, we introduce ComFusion, an innovative approach that leverages pretrained models to create compositions of user-supplied subject images and predefined text scenes. ComFusion incorporates a class-scene prior preservation regularization, which combines subject class and scene-specific knowledge from pretrained models to enhance generation fidelity. Additionally, ComFusion uses coarse-generated images to ensure alignment with both the instance images and scene texts, thereby achieving a delicate balance between capturing the subject’s essence and maintaining scene fidelity. Extensive evaluations of ComFusion against various baselines in T2I personalization have demonstrated its qualitative and quantitative superiority."

"Text-to-Image (T2I) generation has made significant advancements with the advent of diffusion models. These models exhibit remarkable abilities to produce images based on textual prompts. Current T2I models allow users to specify object colors using linguistic color names. However, these labels encompass broad color ranges, making it difficult to achieve precise color matching. To tackle this challenging task, named color prompt learning, we propose to learn specific color prompts tailored to user-selected colors. Existing T2I personalization methods tend to result in color-shape entanglement. To overcome this, we generate several basic geometric objects in the target color, allowing for color and shape disentanglement during the color prompt learning. Our method, denoted as , successfully assists the T2I models to peel off the novel color prompts from these colored shapes. In the experiments, we demonstrate the efficacy of in achieving precise color generation with T2I models. Furthermore, we generalize to effectively learn abstract attribute concepts, including textures, materials, etc. Our findings represent a significant step towards improving precision and versatility of T2I models, offering new opportunities for creative applications and design tasks. Our project is available at https://moatifbutt.github.io/colorpeel/."

"How to effectively explore spatial-temporal features is important for video colorization. Instead of stacking multiple frames along the temporal dimension or recurrently propagating estimated features that will accumulate errors or cannot explore information from far-apart frames, we develop a memory-based feature propagation module that can establish reliable connections with features from far-apart frames and alleviate the influence of inaccurately estimated features. To extract better features from each frame for the above-mentioned feature propagation, we explore the features from large-pretrained visual models to guide the feature estimation of each frame so that the estimated features can model complex scenarios. In addition, we note that adjacent frames usually contain similar contents. To explore this property for better spatial and temporal feature utilization, we develop a local attention module to aggregate the features from adjacent frames in a spatial-temporal neighborhood. We formulate our memory-based feature propagation module, large-pretrained visual model guided feature estimation module, and local attention module into an end-to-end trainable network (named ColorMNet) and show that it performs favorably against state-of-the-art methods on both the benchmark datasets and real-world scenarios. Our source codes and pre-trained models are available at: https://github.com/yyang181/colormnet."

"Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations, existing works have focused on replacing standard random masking with more sophisticated strategies, such as adversarial-guided and teacher-guided masking. However, these strategies depend on the input data thus commonly increasing the model complexity and requiring additional calculations to generate the mask patterns. This raises the question: Can we enhance MAE performance beyond random masking without relying on input data or incurring additional computational costs? In this work, we introduce a simple yet effective data-independent method, termed , which generates different binary mask patterns by filtering random noise. Drawing inspiration from color noise in image processing, we explore four types of filters to yield mask patterns with different spatial and semantic priors. requires no additional learnable parameters or computational overhead in the network, yet it significantly enhances the learned representations. We provide a comprehensive empirical evaluation, demonstrating our strategy’s superiority in downstream tasks compared to random masking. Notably, we report an improvement of 2.72 in mIoU in semantic segmentation tasks relative to baseline MAE implementations."

"Pre-trained vision-language models, e.g. CLIP, have been increasingly used to address the challenging Open-Vocabulary Segmentation (OVS) task, benefiting from their well-aligned vision-text embedding space. Typical solutions involve either freezing CLIP during training to unilaterally maintain its zero-shot capability, or fine-tuning CLIP vision encoder to achieve perceptual sensitivity to local regions. However, few of them incorporate vision-text collaborative optimization. Based on this, we propose the Content-Dependent Transfer to adaptively enhance each text embedding by interacting with the input image, which presents a parameter-efficient way to optimize the text representation. Besides, we additionally introduce a Representation Compensation strategy, reviewing the original CLIP-V representation as compensation to maintain the zero-shot capability of CLIP. In this way, the vision and text representation of CLIP are optimized collaboratively, enhancing the alignment of the vision-text feature space. To the best of our knowledge, we are the first to establish the collaborative vision-text optimizing mechanism within the OVS field. Extensive experiments demonstrate our method achieves superior performance on popular OVS benchmarks. In open-vocabulary semantic segmentation, our method outperforms the previous state-of-the-art approaches by +0.5, +2.3, +3.4, +0.4 and +1.1 mIoU, respectively on A-847, A-150, PC-459, PC-59 and PAS-20. Furthermore, in a panoptic setting on ADE20K, we achieve the performance of 27.1 PQ, 73.5 SQ, and 32.9 RQ. Code will be available at MAFT-Plus."

"Graphics pipelines require physically-based rendering (PBR) materials, yet current 3D content generation approaches are built on RGB models. We propose to model the PBR image distribution directly, avoiding photometric inaccuracies in RGB generation and the inherent ambiguity in extracting PBR from RGB. As existing paradigms for cross-modal fine-tuning are not suited for PBR generation due to both a lack of data and the high dimensionality of the output modalities, we propose to train a new PBR model that is tightly linked to a frozen RGB model using a novel cross-network communication paradigm. As the base RGB model is fully frozen, the proposed method retains its general performance and remains compatible with IPAdapters for that base model."

"The field of 3D reconstruction from images has rapidly evolved in the past few years, first with the introduction of Neural Radiance Field (NeRF) and more recently with 3D Gaussian Splatting (3DGS). The latter provides a significant edge over NeRF in terms of the training and inference speed, as well as the reconstruction quality. Although 3DGS works well for dense input images, the unstructured point-cloud like representation quickly overfits to the more challenging setup of extremely sparse input images (e.g., 3 images), creating a representation that appears as a jumble of needles from novel views. To address this issue, we propose regularized optimization and depth-based initialization. Our key idea is to introduce a structured Gaussian representation that can be controlled in 2D image space. We then constraint the Gaussians, in particular their position, and prevent them from moving independently during optimization. Specifically, we introduce single and multiview constraints through an implicit convolutional decoder and a total variation loss, respectively. With the coherency introduced to the Gaussians, we further constrain the optimization through a flow-based loss function. To support our regularized optimization, we propose an approach to initialize the Gaussians using monocular depth estimates at each input view. We demonstrate significant improvements compared to the state-of-the-art sparse-view NeRF-based approaches on a variety of scenes."