3D Vision Algorithm Intern (3D Human Reconstruction & Tracking)
发布于 大约 8 小时前实习/见习
AI 估算 · 8k–15k
Intern position in Sydney with competitive tech industry stipend, approximate conversion from AUD to CNY based on typical rates.
职位详情
关于这个职位
As a 3D Vision Algorithm Intern at Meitu's Sydney lab, you will work on human aesthetic enhancement and 3D reconstruction technologies. You'll implement state-of-the-art algorithms, collaborate with data teams, and contribute to both production and research outcomes.
最低要求
Experience: PhD candidate in Computer Science, Artificial Intelligence, Intelligent Arts, or related fields. Proficient in Python, with experience using common libraries (e.g., NumPy, Transformers, Diffusers, Open3D), and strong hands-on experience with deep learning frameworks such as PyTorch. Strong, sustained interest in image/video aesthetics or 3D art; resilient mindset and openness to change. Skills & Abilities: Solid engineering implementation skills and rigorous experimental practices; able to independently complete module-level tasks. Proficient with AI-assisted programming tools; maintains clean, well-structured code. Strong ability to read, analyze, summarize, and reproduce academic papers. Clear logical thinking, strong problem-decomposition skills, and curiosity about underlying principles. Motivation & Values: Long-term interest in AI + imaging / 3D / aesthetics. Proactive, self-driven, and willing to explore new approaches and challenges. Alignment with a product culture centered on user experience and technical value.
工作职责
Research and implement algorithms related to depth estimation, multi-view generation, and 2D / 3D tracking with spatiotemporal reconstruction. Follow state-of-the-art 3D vision papers and open-source projects; reproduce experiments and adapt methods to practical applications. Collaborate with data teams to refine the 3D aesthetic development pipeline, improve data collection and quality evaluation, and establish foundations for high-quality scaling. Explore the integration of human structure priors (Skeleton / SMPL / Mesh) with multi-modal cues such as depth, normals, and optical flow in reconstruction and generative models. Assist in building data processing, evaluation, and visualization tools (e.g., immersive video aesthetic editing) to support rapid iteration. Enable high-quality projection of 3D features into 2D visual outputs, with the goal of producing A-level or above academic publications.
优先资格
Bonus Points: Prior experience with SMPL, human pose estimation, 3D reconstruction, or tracking. Familiarity with video understanding, diffusion models, autoregressive models, or flow-matching methods. Research projects, competitions, or open-source contributions. Strong mathematical or geometric intuition; excellent aesthetic sensibility and passion for high-quality design.
AI 洞察
优缺点分析
优点
- Work on cutting-edge 3D vision and human modeling research with direct product impact.
- Access to large-scale real-world datasets and state-of-the-art algorithms.
- Potential for high-quality academic publications alongside production work.
- Located in Sydney with a collaborative, research-oriented team.
- High expectations for research output and engineering quality within a limited internship duration.
- Requires strong self-motivation and ability to work independently on complex problems.
- Competitive field
- need to stay updated with rapid advancements in 3D vision and generative models.
- PhD candidates passionate about 3D vision, human modeling, and aesthetic AI who enjoy both research and implementation.
缺点 / 挑战
暂无明显挑战项
角色解读
- Transition to full-time research scientist or engineer in 3D vision at Meitu or similar companies.
- Opportunity to publish papers at top conferences (CVPR, ICCV, etc.) and contribute to real-world products.
- Build expertise in human modeling and aesthetic AI, opening doors in AR/VR, gaming, and film industries.
- Implement and research algorithms for 3D human reconstruction, tracking, and aesthetic enhancement.
- Work with product-scale datasets and reproduce state-of-the-art papers.
- Collaborate with data teams to improve data pipelines and evaluation tools.
- Integrate human priors (SMPL, skeleton) with multi-modal cues in generative models.
- Strong Python and PyTorch skills with experience in 3D vision libraries (Open3D, etc.).
- Solid understanding of 3D reconstruction, human pose estimation, and tracking.
- Ability to read, analyze, and reproduce academic research papers.
- Familiarity with diffusion models, video understanding, and coding best practices.
申请策略
- Tailor your application to show genuine interest in aesthetics and AI-powered imaging.
- Prepare to discuss specific projects where you solved 3D vision problems or improved visual quality.
- Emphasize experience with SMPL, human pose estimation, or 3D reconstruction projects.
- Highlight any publications, open-source contributions, or competitions in computer vision.
- Showcase strong programming skills (Python, PyTorch) and ability to reproduce papers.
- Mention familiarity with diffusion models, video understanding, and aesthetic design.
- Practice implementing and fine-tuning 3D vision models (e.g., SMPL, NeRF) from scratch.
- Study recent papers on human tracking and generative models to be ready for discussion.
面试指南
- Use STAR method (Situation, Task, Action, Result) for experience-based questions.
- For technical questions, explain the problem, your proposed approach, and trade-offs.
- Show enthusiasm for research by mentioning specific papers or projects you admire.
- Describe your experience with 3D reconstruction or human pose estimation. What challenges did you face?
- How would you approach fine-tuning a diffusion model for human image generation?
- Explain the SMPL model and how it can be used in tracking or reconstruction.
- Tell us about a time you reproduced a state-of-the-art paper and adapted it to a practical problem.
- How do you stay updated with the latest research in 3D vision?
职位点评
Cutting-edge 3D vision internship with strong research focus, limited financial compensation, and on-site work in Sydney.
薪资福利
Intern position with typical stipend; no explicit benefits mentioned, and salary is not disclosed in JD.
成长发展
Highly developmental: opportunity to work on cutting-edge research, publish papers, and gain hands-on experience with production systems.
工作生活
On-site internship in Sydney Central, no WLB signals mentioned; standard full-time hours expected.
使命价值
Mission-driven company focused on beauty and AI; work has social impact through aesthetics and creativity enhancement.