Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown promising results for static scenes, they struggle with dynamic content and typically rely on pre-computed camera poses. We present 4D3R, a pose-free dynamic neural rendering framework that decouples static and dynamic components through a two-stage approach. Our method first leverages 3D foundational models for initial pose and geometry estimation, followed by motion-aware refinement. 4D3R introduces two key technical innovations: (1) a motion-aware bundle adjustment (MA-BA) module that combines transformer-based learned priors with SAM2 for robust dynamic object segmentation, enabling more accurate camera pose refinement; and (2) an efficient Motion-Aware Gaussian Splatting (MA-GS) representation that uses control points with a deformation field MLP and linear blend skinning to model dynamic motion, significantly reducing computational cost while maintaining high-quality reconstruction. Extensive experiments on real-world dynamic datasets demonstrate that our approach achieves up to 1.8dB PSNR improvement over state-of-the-art methods, particularly in challenging scenarios with large dynamic objects, while reducing computational requirements by 5× compared to previous dynamic scene representations.

3D scene segmentation based on neural implicit representation has emerged recently with the advantage of training only on 2D supervision. However, existing approaches still requires expensive per-scene optimization that prohibits generalization to novel scenes during inference. To circumvent this problem, we introduce a \textit{generalizable} 3D segmentation framework based on implicit representation. Specifically, our framework takes in multi-view image features and semantic maps as the inputs instead of only spatial information to avoid overfitting to scene-specific geometric and semantic information. We propose a novel soft voting mechanism to aggregate the 2D semantic information from different views for each 3D point. In addition to the image features, view difference information is also encoded in our framework to predict the voting scores. Intuitively, this allows the semantic information from nearby views to contribute more compared to distant ones. Furthermore, a visibility module is also designed to detect and filter out detrimental information from occluded views. Due to the generalizability of our proposed method, we can synthesize semantic maps or conduct 3D semantic segmentation for novel scenes with solely 2D semantic supervision. Experimental results show that our approach achieves comparable performance with scene-specific approaches. More importantly, our approach can even outperform existing strong supervision-based approaches with only 2D annotations.

PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase the safety of the operation through context-sensitive warnings and semi-autonomous robotic assistance or improve training of surgeons via data-driven feedback. In surgical workflow analysis up to 91% average precision has been reported for phase recognition on an open data single-center video dataset. In this work we investigated the generalizability of phase recognition algorithms in a multicenter setting including more difficult recognition tasks such as surgical action and surgical skill. METHODS: To achieve this goal, a dataset with 33 laparoscopic cholecystectomy videos from three surgical centers with a total operation time of 22 h was created. Labels included framewise annotation of seven surgical phases with 250 phase transitions, 5514 occurences of four surgical actions, 6980 occurences of 21 surgical instruments from seven instrument categories and 495 skill classifications in five skill dimensions. The dataset was used in the 2019 international Endoscopic Vision challenge, sub-challenge for surgical workflow and skill analysis. Here, 12 research teams trained and submitted their machine learning algorithms for recognition of phase, action, instrument and/or skill assessment. RESULTS: F1-scores were achieved for phase recognition between 23.9% and 67.7% (n = 9 teams), for instrument presence detection between 38.5% and 63.8% (n = 8 teams), but for action recognition only between 21.8% and 23.3% (n = 5 teams). The average absolute error for skill assessment was 0.78 (n = 1 team). CONCLUSION: Surgical workflow and skill analysis are promising technologies to support the surgical team, but there is still room for improvement, as shown by our comparison of machine learning algorithms. This novel HeiChole benchmark can be used for comparable evaluation and validation of future work. In future studies, it is of utmost importance to create more open, high-quality datasets in order to allow the development of artificial intelligence and cognitive robotics in surgery.

Part segmentations provide a rich and detailed part-level description of objects. However, their annotation requires an enormous amount of work, which makes it difficult to apply standard deep learning methods. In this paper, we propose the idea of learning part segmentation through unsupervised domain adaptation (UDA) from synthetic data. We first introduce UDA-Part, a comprehensive part segmentation dataset for vehicles that can serve as an adequate benchmark for UDA11https://qliu24.github.io/udapart/. In UDA-Part, we label parts on 3D CAD models which enables us to generate a large set of annotated synthetic images. We also annotate parts on a number of real images to provide a real test set. Secondly, to advance the adaptation of part models trained from the synthetic data to the real images, we introduce a new UDA algorithm that leverages the object's spatial structure to guide the adaptation process. Our experimental results on two real test datasets confirm the superiority of our approach over existing works, and demonstrate the promise of learning part segmentation for general objects from synthetic data. We believe our dataset provides a rich testbed to study UDA for part segmentation and will help to significantly push forward research in this area.

In 1975, J. E. Mazo showed the potential faster‐than‐Nyquist (FTN) gain of the single‐carrier binary signal. If the inter‐symbol interference is eliminated by an optimal detector, FTN single‐carrier binary signal can transmit 24.7% more bits than the Nyquist signal without loss of bit error rate performance, which is known as the Mazo limit. In this study, the authors apply sphere decoder (SD) with box optimisation (BO) to reduce inter‐carrier interference (ICI) in the FTN non‐orthogonal frequency division multiplexing (FTN–NOFDM) system. Compared with the commonly used SD algorithm, SD with BO can achieve the same ICI cancellation performance, and the computational complexity is significantly reduced. When the bandwidth compression factor is set to 0.802, the transmission rate of FTN–NOFDM is 24.7% faster than the Nyquist rate, and quadrature phase shift keying (QPSK)‐modulated FTN–NOFDM has almost the same performance as QPSK‐modulated orthogonal frequency division multiplexing (OFDM), which agrees well with Mazo limit. In the simulation, the QPSK‐modulated FTN–NOFDM with outperforms 16‐quadrature amplitude modulation (16‐QAM)‐modulated OFDM by about 1.5 dB, and the 16‐QAM‐modulated FTN–NOFDM with and outperforms 64‐ and 256‐QAM‐modulated OFDM by about 1.5 and 2 dB, respectively.

Carbon/carbon composites are very important compound in our daily life. Pyrocarbon texture has sharp transition phenomenon under extreme heat condition. As the particles react randomly in the phenomenon, Monte Carlo method is embraced to investigate such mechanism based on Langmuir-Hinshelwood (L-H) mechanism of Particle-Filler (P-F) conceptual model. However, the single thread investigating program consumes huge time for simulating the chemical reaction on the hexagonal-mesh surface billion times and the computing cost. In this paper, this paper proposes an approach for accelerating the P-F modeling process with HMSPM (Hexagonal-Mesh Surface Position Map). Such approach can reduce computation complexity from search reaction position randomly. What's more, HMSPM can reduce loops by simulating reaction position parallel with reaction position conflict. To evaluate our accelerating approach, the executing time of serial program and the program with our approach were compared. The result shows that the computational time can shorten 23561%. This paper's accelerating method has the same result of the MT/HT transition phenomenon with formula parameter `R' and `a'.