3D Gaussian splatting (3D-GS) is a new rendering approach that outperforms the neural radiance field (NeRF) in terms of both speed and image quality. 3D-GS represents 3D scenes by utilizing millions of 3D Gaussians and projects these Gaussians onto the 2D image plane for rendering. However, during the rendering process, a substantial number of unnecessary 3D Gaussians exist for the current view direction, resulting in significant computation costs associated with their identification. In this paper, we propose a computational reduction technique that quickly identifies unnecessary 3D Gaussians in real-time for rendering the current view without compromising image quality. This is accomplished through the offline clustering of 3D Gaussians that are close in distance, followed by the projection of these clusters onto a 2D image plane during runtime. Additionally, we analyze the bottleneck associated with the proposed technique when executed on GPUs and propose an efficient hardware architecture that seamlessly supports the proposed scheme. For the Mip-NeRF360 dataset, the proposed technique excludes 63% of 3D Gaussians on average before the 2D image projection, which reduces the overall rendering computation by almost 38.3% without sacrificing peak-signal-to-noise-ratio (PSNR). The proposed accelerator also achieves a speedup of 10.7x compared to a GPU.
In this paper we propose a reinforcement learning based weakly supervised system for localisation. We train a controller function to localise regions of interest within an image by introducing a novel reward definition that utilises non-binarised classification probability, generated by a pre-trained binary classifier which classifies object presence in images or image crops. The object-presence classifier may then inform the controller of its localisation quality by quantifying the likelihood of the image containing an object. Such an approach allows us to minimize any potential labelling or human bias propagated via human labelling for fully supervised localisation. We evaluate our proposed approach for a task of cancerous lesion localisation on a large dataset of real clinical bi-parametric MR images of the prostate. Comparisons to the commonly used multiple-instance learning weakly supervised localisation and to a fully supervised baseline show that our proposed method outperforms the multi-instance learning and performs comparably to fully-supervised learning, using only image-level classification labels for training.
Higher spatial resolution and larger imaging scene are always the goals pursued by advanced space-borne SAR system.High resolution and wide swath SAR imaging can provide more information about the illuminated scene of interest on one hand,but also come with some new challenges on the other hand.The induced new challenging problems include curved orbit,Earth rotation,and spherical ground surface,etc.Most existing image formation algorithms suffer from performance deficiency in these challenging cases,either in focus accuracy or computational efficiency.In this paper,an accurate Fourier transform relationship between the phase history domain data and the scene reflectivity function is derived under arbitrary radar trajectory by exploiting the spherical geometry property of the space-borne SAR data collection.Using the derived new data model,an image reconstruction algorithm based on Fourier inversion is proposed.The new algorithm has the inherent capability of correcting for the curved orbit and spherical ground surface effect.Meanwhile,the out-of-plane motion effect induced by the Earth's rotation can also be compensated by a two-step phase correction and data projection procedure embedded in the Fourier inversion reconstruction.The new algorithm inherits the merit of both time domain and frequency domain algorithms,has excellent performance in both focus accuracy and computational efficiency.Both simulation and real data processing results validate the effectiveness of the proposed imaging algorithm.
Imaging Mueller polarimetry has already proved its potential for metrology, remote sensing and biomedicine. The real-time applications of this modality require both video rate image acquisition and fast data post-processing algorithms. First, one must check the physical realizability of the experimental Mueller matrices in order to filter out non-physical data, i.e. to test the positive semi-definiteness of the 4x4 Hermitian coherency matrix calculated from the elements of the corresponding Mueller matrix pixel-wise. For this purpose, we compared the execution time for the calculations of i) eigenvalues, ii) Cholesky decomposition, iii) Sylvester's criterion, and iv) coefficients of the characteristic polynomial of the Hermitian coherency matrix using two different approaches, all calculated for the experimental Mueller matrix images (600 pixels x 700 pixels) of mouse uterine cervix. The calculations were performed using C++ and Julia programming languages. Our results showed the superiority of the algorithm iv), in particular, the version based on the simplification via Pauli matrices, in terms of execution time for our dataset, over other algorithms. The sequential implementation of the latter algorithm on a single core already satisfies the requirements of real-time polarimetric imaging in various domains. This can be further amplified by the proposed parallelization (for example, we achieve a 5-fold speed up on 6 cores).
Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in the training dataset, we often are more concerned with other properties, such as the aesthetic quality of the generated images or the functional properties of generated proteins. Diffusion models can be finetuned in a goal-directed way by maximizing the value of some reward function (e.g., the aesthetic quality of an image). However, these approaches may lead to reduced sample diversity, significant deviations from the training data distribution, and even poor sample quality due to the exploitation of an imperfect reward function. The last issue often occurs when the reward function is a learned model meant to approximate a ground-truth "genuine" reward, as is the case in many practical applications. These challenges, collectively termed "reward collapse," pose a substantial obstacle. To address this reward collapse, we frame the finetuning problem as entropy-regularized control against the pretrained diffusion model, i.e., directly optimizing entropy-enhanced rewards with neural SDEs. We present theoretical and empirical evidence that demonstrates our framework is capable of efficiently generating diverse samples with high genuine rewards, mitigating the overoptimization of imperfect reward models.
Multimodal pretraining has emerged as an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progression information; 2) enforcing temporal consistency of visual representation; 3) capturing trajectory-level language grounding. Most existing methods approach these via separate objectives, which often reach sub-optimal solutions. In this paper, we propose a universal unified objective that can simultaneously extract meaningful task progression information from image sequences and seamlessly align them with language instructions. We discover that via implicit preferences, where a visual trajectory inherently aligns better with its corresponding language instruction than mismatched pairs, the popular Bradley-Terry model can transform into representation learning through proper reward reparameterizations. The resulted framework, DecisionNCE, mirrors an InfoNCE-style objective but is distinctively tailored for decision-making tasks, providing an embodied representation learning framework that elegantly extracts both local and global task progression features, with temporal consistency enforced through implicit time contrastive learning, while ensuring trajectory-level instruction grounding via multimodal joint encoding. Evaluation on both simulated and real robots demonstrates that DecisionNCE effectively facilitates diverse downstream policy learning tasks, offering a versatile solution for unified representation and reward learning. Project Page: https://2toinf.github.io/DecisionNCE/
Model inversion attacks (MIAs) seek to infer the private training data of a target classifier by generating synthetic images that reflect the characteristics of the target class through querying the model. However, prior studies have relied on full access to the target model, which is not practical in real-world scenarios. Additionally, existing black-box MIAs assume that the image prior and target model follow the same distribution. However, when confronted with diverse data distribution settings, these methods may result in suboptimal performance in conducting attacks. To address these limitations, this paper proposes a \textbf{C}onfidence-\textbf{G}uided \textbf{M}odel \textbf{I}nversion attack method called CG-MI, which utilizes the latent space of a pre-trained publicly available generative adversarial network (GAN) as prior information and gradient-free optimizer, enabling high-resolution MIAs across different data distributions in a black-box setting. Our experiments demonstrate that our method significantly \textbf{outperforms the SOTA black-box MIA by more than 49\% for Celeba and 58\% for Facescrub in different distribution settings}. Furthermore, our method exhibits the ability to generate high-quality images \textbf{comparable to those produced by white-box attacks}. Our method provides a practical and effective solution for black-box model inversion attacks.
Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However, DMs reflect the biases present in the training datasets. This is especially concerning in the context of faces, where the DM prefers one demographic subgroup vs others (eg. female vs male). In this work, we present a method for debiasing DMs without relying on additional data or model retraining. Specifically, we propose Distribution Guidance, which enforces the generated images to follow the prescribed attribute distribution. To realize this, we build on the key insight that the latent features of denoising UNet hold rich demographic semantics, and the same can be leveraged to guide debiased generation. We train Attribute Distribution Predictor (ADP) - a small mlp that maps the latent features to the distribution of attributes. ADP is trained with pseudo labels generated from existing attribute classifiers. The proposed Distribution Guidance with ADP enables us to do fair generation. Our method reduces bias across single/multiple attributes and outperforms the baseline by a significant margin for unconditional and text-conditional diffusion models. Further, we present a downstream task of training a fair attribute classifier by rebalancing the training set with our generated data.
Despite numerous completed studies, achieving high fidelity talking face generation with highly synchronized lip movements corresponding to arbitrary audio remains a significant challenge in the field. The shortcomings of published studies continue to confuse many researchers. This paper introduces G4G, a generic framework for high fidelity talking face generation with fine-grained intra-modal alignment. G4G can reenact the high fidelity of original video while producing highly synchronized lip movements regardless of given audio tones or volumes. The key to G4G's success is the use of a diagonal matrix to enhance the ordinary alignment of audio-image intra-modal features, which significantly increases the comparative learning between positive and negative samples. Additionally, a multi-scaled supervision module is introduced to comprehensively reenact the perceptional fidelity of original video across the facial region while emphasizing the synchronization of lip movements and the input audio. A fusion network is then used to further fuse the facial region and the rest. Our experimental results demonstrate significant achievements in reenactment of original video quality as well as highly synchronized talking lips. G4G is an outperforming generic framework that can produce talking videos competitively closer to ground truth level than current state-of-the-art methods.
In the rapidly evolving landscape of deep learning, the quest for models that balance expressivity with computational efficiency has never been more critical. This paper introduces Orchid, a novel architecture that reimagines sequence modeling by incorporating a new data-dependent convolution mechanism. Orchid is designed to address the inherent limitations of traditional attention mechanisms, particularly their quadratic complexity, without compromising the ability to capture long-range dependencies and in-context learning. At the core of Orchid lies the data-dependent convolution layer, which dynamically adjusts its kernel conditioned on input data using a dedicated conditioning neural network. We design two simple conditioning networks that maintain shift equivariance in the adaptive convolution operation. The dynamic nature of data-dependent convolution kernel, coupled with gating operations, grants Orchid high expressivity while maintaining efficiency and quasilinear scalability for long sequences. We rigorously evaluate Orchid across multiple domains, including language modeling and image classification, to showcase its performance and generality. Our experiments demonstrate that Orchid architecture not only outperforms traditional attention-based architectures such as BERT and Vision Transformers with smaller model sizes, but also extends the feasible sequence length beyond the limitations of the dense attention layers. This achievement represents a significant step towards more efficient and scalable deep learning models for sequence modeling.